feat: task_completed signal — post-task skill capture (v0.3.2)

Adds an 11th signal type emitted when a run of work (between two
UserPromptSubmit events) crosses three quality gates:
  - >=5 tool calls (TASK_TOOL_MIN)
  - >=3 distinct tool kinds (TASK_DIVERSITY_MIN, filters single-tool
    sweeps like "wrote 5 files")
  - 0 correction signals during the run (filters tasks where the user
    pushed back; correction-during-task disqualifies the recipe)

Payload carries tool_count, tool_kinds, active_skills, active_agents
so the agent can cluster by sorted tool-kind tuple and route through
the existing skill-overlap rule (skill_new vs skill_edit).

Importantly: cross_session_evidence is FALSE on first occurrence,
so resulting skill_new proposals always queue for review — they only
auto-apply when the same multi-tool recipe recurs in a second session
(then the existing rubric kicks in). Post-task creation captures novel
patterns while preserving the rule "auto-apply requires cross-session".

Hook adds state fields: task_tool_count, task_tool_kinds, task_corrections.
All reset on UserPromptSubmit boundary and on session change.

Agent gets one new signal-types-table row and one clustering bullet
referencing the existing skill-overlap rule.

3 new tests (30 passed, 0 failed):
  - 5 tools + 5 kinds + 0 corrections fires task_completed
  - 5 tools + 1 kind (Edit only) does NOT fire (diversity gate)
  - 5 tools + 3 kinds + correction-on-closing-prompt does NOT fire

README.md

@@ -2,6 +2,13 @@
 
 Self-improvement layer for [Claude Code](https://claude.com/claude-code) that observes friction signals during your sessions and proposes targeted improvements (new skills, memory entries, agent edits) which you can review and apply.
 
+## What's new
+
+- **v0.3.1** — code review pass: bug fixes (`errorFingerprint` no longer false-positives on `is_error: false`, archive script handles same-millisecond duplicates correctly, `tool_window` now clears on session change, nudge filters proposal filenames by pattern), prose conciseness cuts, hardened `install.sh` with curl one-liner + settings.json merge, `adam-uninstall.sh`, isolated test harness (no longer pollutes live `~/.claude/adam/` state).
+- **v0.3.0** — causal diagnosis: every proposal carries a `# Diagnosis` block (Trigger/Action/Mismatch/Outcome with verbatim transcript quote) before drafting, plus optional `contradiction_flag` heuristic that vetoes auto-apply on obviously-conflicting `skill_edit` additions.
+- **v0.2.1** — win signals (`correction_free_streak`, `clean_recovery`) feed `skill_edit` auto-apply under a strict gate (≤30 LOC, ≤2× byte cap, 7d cooldown, 30d blacklist on rejection).
+- **v0.2.0** — actioned-entry archival via `adam-archive.mjs`; `cursor` field deprecated.
+
 ## What it does
 
 A lightweight Node.js hook (`adam-observe.mjs`) runs on `UserPromptSubmit`, `PreToolUse`, and `PostToolUse` events. It detects:
@@ -16,6 +23,8 @@ A lightweight Node.js hook (`adam-observe.mjs`) runs on `UserPromptSubmit`, `Pre
 | `edit_churn` | Same file edited 4× in a window |
 | `build_loop` | 2× build/test/compile commands fail in same session |
 | `subagent_dispatch_pattern` | Same subagent dispatched ≥3× cumulatively |
+| `correction_free_streak` | 5 clean UserPromptSubmits in a row (no correction phrase) — feeds `skill_edit` reinforcement |
+| `clean_recovery` | 3 clean PostToolUse events after a struggle signal — feeds `skill_edit` reinforcement |
 
 Detection is local, regex-based, zero LLM cost. Signals append to `~/.claude/adam/journal.jsonl`.
 
@@ -36,42 +45,73 @@ LLM coding sessions reveal repeated friction the moment you stop and look. ADAM
 ├── skills/adam-self-improvement/SKILL.md  # /reflect protocol
 ├── commands/reflect.md       # /reflect slash command
 └── adam/
-    ├── journal.jsonl         # append-only signal log
-    ├── journal/              # rotated daily logs (>5 MB threshold)
-    ├── state.json            # cursor + per-session counters
-    ├── usage.json            # skill/agent invocation tallies
+    ├── journal.jsonl         # append-only signal log (active observations)
+    ├── journal/              # rotated daily logs + actioned-<id>.jsonl per applied/rejected proposal
+    ├── state.json            # per-session counters
+    ├── usage.json            # skill/agent invocation tallies + payload visibility counters
     ├── proposals/            # queued, awaiting review
     ├── applied/              # approved + auto-applied archive
     ├── rejected/             # rejected (with reason)
     ├── trash/                # soft-deleted artifacts (recoverable)
-    └── tests/run-tests.sh    # 18 verification tests
+    ├── scripts/              # adam-archive.mjs (called by skill on apply/reject)
+    └── tests/run-tests.sh    # 27 verification tests (isolated tmpdir; never touches live state)
 ```
 
 ## Install
 
+### One-liner (recommended)
+
 ```sh
+curl -fsSL https://raw.githubusercontent.com/lukaszraczylo/claude-adam/main/install.sh | bash
+```
+
+Pin a release for reproducibility:
+
+```sh
+curl -fsSL https://raw.githubusercontent.com/lukaszraczylo/claude-adam/v0.3.1/install.sh \
+  | VERSION=v0.3.1 bash
+```
+
+The installer clones the repo to `/tmp`, copies files into `~/.claude/`, and offers to merge ADAM's hook entries into your `~/.claude/settings.json` (with a diff preview and `[y/N]` confirmation — your existing hooks are preserved). Pass `--yes` to skip the prompt; `--dry-run` to preview without writing.
+
+Requires `git`, `curl`, `jq`, and `node` 18+.
+
+### From a clone
+
+```sh
+git clone https://github.com/lukaszraczylo/claude-adam
+cd claude-adam
 ./install.sh
 ```
 
-The script copies files into `~/.claude/`. **It does NOT modify your `settings.json`** — wire the hook entries manually using `settings.json.example` as reference. Merging into existing settings prevents accidental clobber of your other hooks.
+### Upgrade-safe
 
-After install:
-1. Run the test suite: `bash ~/.claude/adam/tests/run-tests.sh` — must show `18 passed, 0 failed`.
-2. Add the hook entries from `settings.json.example` to `~/.claude/settings.json` (preserve your existing hooks; ADAM's are additive).
-3. Restart Claude Code, or just run `/reflect` to trigger the skill — Claude Code v2.1.0+ auto-hot-reloads user-level skills, no restart needed.
+These files are **never overwritten** if they already exist:
+
+- `~/.claude/adam/journal.jsonl` — your observation log
+- `~/.claude/adam/state.json` — session counters
+- `~/.claude/adam/usage.json` — invocation tallies
+
+If you've locally edited any installed file (e.g. `agents/adam.md`), the installer writes the new version to `<file>.adam-new` and warns you instead of clobbering.
+
+After install: run `bash ~/.claude/adam/tests/run-tests.sh` to verify (expect `27 passed, 0 failed`), start a fresh Claude Code session, then run `/reflect`.
 
 ## Requirements
 
 - Claude Code v2.1.0+ (for auto skill hot-reload; older versions need session restart after `skill_new` proposals are applied)
 - Node.js 18+ (for the hook; tested on v22)
-- Bash (for the test harness)
+- Bash 4+, `git`, `curl`, `jq` (for installer + test harness)
+
+### Platform support
+
+Tested on **macOS** (Darwin / BSD coreutils) and **Linux** (Alpine, glibc + musl). The install / uninstall / test scripts are written to be portable: `stat` uses BSD `-f` with GNU `-c` fallback, `mktemp -d -t prefix.XXXXXX` works on both, no GNU-only flags. CI smoke verified `27 passed, 0 failed` under `alpine:latest`.
 
 ## Confidence rubric
 
 ```
 Sum:
 +2  Signal repeated ≥3× across ≥2 sessions
-+2  Struggle signal repeated ≥3× within a single session (does not stack with above)
++2  Struggle signal appearing ≥1× within a single session (does not stack)
 +2  Transcript contains positive endorsement near related action
 +1  Multi-axis cluster (≥2 distinct struggle types in same session)
 -1  Type-bias penalty (≥3 rejections, applied:rejected <1:2)
@@ -84,10 +124,26 @@ Sum:
 auto_apply_eligible requires ALL:
   confidence ≥ 4
   blast_radius == low
-  type ∈ {memory, skill_new}
+  type ∈ {memory, skill_new, skill_edit}     # skill_edit also passes the win-driven gate
   cross_session_evidence == true (single-session-only proposals always queue)
+
+skill_edit additionally requires (v0.2.1+):
+  win-signal evidence (correction_free_streak / clean_recovery cites target skill)
+  diff is append-only, ≤30 LOC, resulting size ≤2× original
+  no auto-edit to same target in past 7 days (cooldown)
+  no rejection-blacklist on target in past 30 days
+  contradiction heuristic does not flag (v0.3.0+)
+  # Diagnosis section present + structurally valid (v0.3.0+)
 ```
 
+## Lifecycle: how proposals become permanent
+
+Every proposal records the journal entry timestamps that fed its cluster (`source_entries` in frontmatter). When you apply or reject a proposal, the skill calls `adam/scripts/adam-archive.mjs` which moves matching entries from `journal.jsonl` to `journal/actioned-<id>.jsonl`. Effects:
+
+- The `journal.jsonl` stays bounded by **active** observations only.
+- The next `/reflect` reads applied/ + rejected/ frontmatter, builds an excluded-timestamps set, and skips any leftover journal entries that were already actioned.
+- Rule changes (e.g. lowering a threshold) immediately re-evaluate the remaining active observations — no manual cursor rewind needed.
+
 ## What it will not do
 
 - No background LLM spend. The analyst runs only when you invoke `/reflect`.
@@ -99,9 +155,22 @@ auto_apply_eligible requires ALL:
 
 ## Uninstall
 
+One-shot:
+
 ```sh
-rm -rf ~/.claude/{hooks/adam-*.mjs,agents/adam.md,skills/adam-self-improvement,commands/reflect.md,adam}
+curl -fsSL https://raw.githubusercontent.com/lukaszraczylo/claude-adam/main/adam-uninstall.sh | bash
 ```
+
+The uninstaller archives `~/.claude/adam/` to `~/.claude/adam.bak.<ts>/` (preserving your journal/proposals data), removes ADAM files, and offers to strip ADAM hook entries from `~/.claude/settings.json` with a diff prompt. Pass `--yes` to skip the prompt; `--purge` to delete the data archive instead of preserving it.
+
+Manual:
+
+```sh
+mv ~/.claude/adam ~/.claude/adam.bak.$(date +%s)
+rm -f ~/.claude/hooks/adam-*.mjs ~/.claude/agents/adam.md ~/.claude/commands/reflect.md
+rm -rf ~/.claude/skills/adam-self-improvement
+```
+
 Then remove the four `adam-*` hook entries from `~/.claude/settings.json`.
 
 ## License

adam-uninstall.sh

@@ -0,0 +1,88 @@
+#!/usr/bin/env bash
+# ADAM uninstaller — reverses install.sh.
+# Soft-archives ~/.claude/adam/ (your journal/proposals are preserved by default).
+# Removes hook entries from settings.json with a diff prompt.
+#
+# Usage: ./adam-uninstall.sh [--yes] [--purge]
+#   --purge: also delete ~/.claude/adam/ data (destructive)
+
+set -euo pipefail
+
+DEST="${HOME}/.claude"
+ASSUME_YES=0
+PURGE=0
+BAK=""
+
+for arg in "$@"; do
+  case "$arg" in
+    --yes|-y)  ASSUME_YES=1 ;;
+    --purge)   PURGE=1 ;;
+    --help|-h) sed -n '2,8p' "$0"; exit 0 ;;
+    *) echo "unknown: $arg" >&2; exit 1 ;;
+  esac
+done
+
+log() { printf '  %s\n' "$*"; }
+need() { command -v "$1" >/dev/null 2>&1 || { echo "missing: $1" >&2; exit 1; }; }
+need jq
+
+[ -d "$DEST" ] || { echo "$DEST not found"; exit 1; }
+
+log "removing ADAM files"
+rm -f  "$DEST/hooks/adam-observe.mjs" "$DEST/hooks/adam-nudge.mjs"
+rm -f  "$DEST/agents/adam.md" "$DEST/commands/reflect.md"
+rm -rf "$DEST/skills/adam-self-improvement"
+
+if [ -d "$DEST/adam" ]; then
+  if [ "$PURGE" = 1 ]; then
+    log "purging $DEST/adam (--purge)"
+    rm -rf "$DEST/adam"
+  else
+    BAK="$DEST/adam.bak.$(date +%s)"
+    log "archiving $DEST/adam -> $BAK"
+    mv "$DEST/adam" "$BAK"
+  fi
+fi
+
+# settings.json — strip ADAM hook entries
+SETTINGS="$DEST/settings.json"
+if [ -f "$SETTINGS" ]; then
+  TMP="$(mktemp -t adam-uninstall.XXXXXX)"
+  jq '
+    .hooks //= {}
+    | .hooks |= with_entries(
+        .value |= (
+          map(.hooks |= map(select(
+            (.command // "") | test("adam-(observe|nudge)\\.mjs") | not
+          )))
+          | map(select((.hooks // []) | length > 0))
+        )
+      )
+    | .hooks |= with_entries(select((.value | length) > 0))
+  ' "$SETTINGS" > "$TMP"
+
+  if cmp -s "$SETTINGS" "$TMP"; then
+    log "settings.json already clean"
+    rm -f "$TMP"
+  else
+    log ""
+    log "settings.json changes:"
+    diff -u "$SETTINGS" "$TMP" | sed 's/^/    /' || true
+    log ""
+    if [ "$ASSUME_YES" = 1 ]; then REPLY=y
+    else printf '  apply? [y/N] '; read -r REPLY </dev/tty || REPLY=n
+    fi
+    case "$REPLY" in
+      y|Y|yes|YES)
+        cp "$SETTINGS" "$SETTINGS.adam-bak.$(date +%s)"
+        mv "$TMP" "$SETTINGS"
+        log "  settings.json cleaned"
+        ;;
+      *) rm -f "$TMP"; log "  skipped — edit settings.json manually" ;;
+    esac
+  fi
+fi
+
+log ""
+log "ADAM uninstalled."
+[ "$PURGE" = 0 ] && [ -n "$BAK" ] && [ -d "$BAK" ] && log "data archive: $BAK"

adam/scripts/adam-archive.mjs

@@ -0,0 +1,122 @@
+#!/usr/bin/env node
+// Usage: adam-archive.mjs <proposal-path>
+// Reads `source_entries` from proposal frontmatter, moves matching journal
+// entries from journal.jsonl to journal/actioned-<id>.jsonl. Used by the
+// adam-self-improvement skill after each apply/reject so subsequent /reflect
+// runs do not re-cluster already-actioned signals.
+
+import { readFileSync, writeFileSync, appendFileSync, mkdirSync, existsSync } from "node:fs";
+import { join } from "node:path";
+import { homedir } from "node:os";
+
+const ROOT = join(homedir(), ".claude", "adam");
+const JOURNAL = join(ROOT, "journal.jsonl");
+const JOURNAL_DIR = join(ROOT, "journal");
+
+function parseFrontmatter(content) {
+  const m = content.match(/^---\n([\s\S]*?)\n---/);
+  if (!m) return {};
+  const fm = {};
+  const lines = m[1].split("\n");
+  let i = 0;
+  while (i < lines.length) {
+    const line = lines[i];
+    const idx = line.indexOf(":");
+    if (idx === -1) { i++; continue; }
+    const key = line.slice(0, idx).trim();
+    const value = line.slice(idx + 1).trim();
+    if (key === "source_entries") {
+      const arr = [];
+      if (value.startsWith("[") && value.endsWith("]")) {
+        const inner = value.slice(1, -1)
+          .split(",")
+          .map(s => s.trim().replace(/^['"]|['"]$/g, ""));
+        arr.push(...inner.filter(Boolean));
+        fm[key] = arr;
+        i++;
+        continue;
+      }
+      i++;
+      while (i < lines.length && /^\s*-\s+/.test(lines[i])) {
+        const item = lines[i].replace(/^\s*-\s+/, "").trim().replace(/^['"]|['"]$/g, "");
+        if (item) arr.push(item);
+        i++;
+      }
+      fm[key] = arr;
+      continue;
+    }
+    fm[key] = value;
+    i++;
+  }
+  return fm;
+}
+
+function main() {
+  const proposalPath = process.argv[2];
+  if (!proposalPath) {
+    console.error("usage: adam-archive.mjs <proposal-path>");
+    process.exit(2);
+  }
+
+  let proposal;
+  try {
+    proposal = readFileSync(proposalPath, "utf8");
+  } catch (e) {
+    console.error(`cannot read ${proposalPath}: ${e.message}`);
+    process.exit(1);
+  }
+
+  const fm = parseFrontmatter(proposal);
+  const id = fm.id || "unknown";
+  const sourceEntries = Array.isArray(fm.source_entries) ? fm.source_entries : [];
+
+  if (sourceEntries.length === 0) {
+    console.log(`${id}: no source_entries in frontmatter — nothing to archive`);
+    return;
+  }
+
+  if (!existsSync(JOURNAL)) {
+    console.log(`${id}: journal does not exist at ${JOURNAL}`);
+    return;
+  }
+
+  const lines = readFileSync(JOURNAL, "utf8").split("\n").filter(Boolean);
+  // tsCounts: how many entries with this ts the proposal claims as its own.
+  // Same-millisecond duplicates: only consume up to the recorded count.
+  const tsCounts = new Map();
+  for (const ts of sourceEntries) tsCounts.set(ts, (tsCounts.get(ts) || 0) + 1);
+  const matched = [];
+  const remaining = [];
+
+  for (const line of lines) {
+    try {
+      const e = JSON.parse(line);
+      const remainingCount = e.ts ? (tsCounts.get(e.ts) || 0) : 0;
+      if (remainingCount > 0) {
+        matched.push(line);
+        tsCounts.set(e.ts, remainingCount - 1);
+      } else {
+        remaining.push(line);
+      }
+    } catch {
+      remaining.push(line);
+    }
+  }
+
+  if (matched.length === 0) {
+    console.log(`${id}: no matching entries in journal (already archived?)`);
+    return;
+  }
+
+  mkdirSync(JOURNAL_DIR, { recursive: true });
+  const archivePath = join(JOURNAL_DIR, `actioned-${id}.jsonl`);
+  appendFileSync(archivePath, matched.join("\n") + "\n");
+  writeFileSync(JOURNAL, remaining.length ? remaining.join("\n") + "\n" : "");
+
+  console.log(`${id}: archived ${matched.length}/${lines.length} entries → ${archivePath}`);
+}
+
+try { main(); } catch (e) {
+  console.error(`error: ${e.message}`);
+  process.exit(1);
+}

adam/scripts/test-hook.mjs

@@ -0,0 +1,154 @@
+#!/usr/bin/env node
+// Test driver for ~/.claude/hooks/adam-observe.mjs.
+// Usage: node test-hook.mjs (runs all tests in this file).
+// Spawns the hook with synthesized stdin in a tmp HOME, asserts journal contents.
+import { spawnSync } from "node:child_process";
+import { mkdtempSync, mkdirSync, readFileSync, existsSync, rmSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { fileURLToPath } from "node:url";
+
+const HOOK = join(fileURLToPath(new URL("../../hooks/adam-observe.mjs", import.meta.url)));
+
+export function newTmpHome() {
+  const home = mkdtempSync(join(tmpdir(), "adam-test-"));
+  mkdirSync(join(home, ".claude/adam"), { recursive: true });
+  return home;
+}
+
+export function feed(home, input) {
+  const r = spawnSync("node", [HOOK], {
+    input: JSON.stringify(input),
+    env: { ...process.env, HOME: home },
+    encoding: "utf8",
+    timeout: 5000,
+  });
+  if (r.status !== 0) throw new Error(`hook exit ${r.status}: ${r.stderr}`);
+  return r;
+}
+
+export function readJournal(home) {
+  const p = join(home, ".claude/adam/journal.jsonl");
+  if (!existsSync(p)) return [];
+  return readFileSync(p, "utf8")
+    .trim().split("\n").filter(Boolean).map((l) => JSON.parse(l));
+}
+
+export function assert(cond, msg) {
+  if (!cond) { console.error(`FAIL: ${msg}`); process.exit(1); }
+  console.log(`ok: ${msg}`);
+}
+
+export function cleanup(home) { try { rmSync(home, { recursive: true, force: true }); } catch {} }
+
+// Tests below this line — added by subsequent tasks.
+
+function testCorrectionFreeStreak() {
+  const home = newTmpHome();
+  try {
+    for (let i = 0; i < 5; i++) {
+      feed(home, {
+        hook_event_name: "UserPromptSubmit",
+        session_id: "s1",
+        cwd: "/x",
+        prompt: `please continue with the work item ${i}`,
+      });
+    }
+    const j = readJournal(home);
+    const streaks = j.filter(e => e.type === "correction_free_streak");
+    assert(streaks.length === 1, "exactly one correction_free_streak after 5 clean prompts");
+    assert(streaks[0].streak === 5, "streak field is 5");
+    assert(streaks[0].session === "s1", "session id captured");
+  } finally { cleanup(home); }
+}
+
+function testStreakResetsOnSessionChange() {
+  const home = newTmpHome();
+  try {
+    // 4 in s1 (counter=4, no streak yet), then 1 in s2 (counter must reset → 1, no streak)
+    for (let i = 0; i < 4; i++) feed(home, { hook_event_name: "UserPromptSubmit", session_id: "s1", cwd: "/x", prompt: "ok" });
+    feed(home, { hook_event_name: "UserPromptSubmit", session_id: "s2", cwd: "/x", prompt: "ok" });
+    const j = readJournal(home);
+    assert(j.filter(e => e.type === "correction_free_streak").length === 0, "no streak when session changes mid-streak");
+  } finally { cleanup(home); }
+}
+
+function testCleanRecovery() {
+  const home = newTmpHome();
+  try {
+    // Trigger tool_error_loop: 3 PostToolUse with same error fingerprint.
+    for (let i = 0; i < 3; i++) {
+      feed(home, {
+        hook_event_name: "PostToolUse",
+        session_id: "s1", cwd: "/x",
+        tool_name: "Bash",
+        tool_input: { command: `echo ${i}` },
+        tool_response: { is_error: true, content: "error: command not found" },
+      });
+    }
+    // Then 3 clean PostToolUse events.
+    for (let i = 0; i < 3; i++) {
+      feed(home, {
+        hook_event_name: "PostToolUse",
+        session_id: "s1", cwd: "/x",
+        tool_name: "Read",
+        tool_input: { file_path: `/tmp/ok-${i}` },
+        tool_response: { content: "fine" },
+      });
+    }
+    const j = readJournal(home);
+    const recs = j.filter(e => e.type === "clean_recovery");
+    assert(recs.length === 1, "one clean_recovery emitted after 3 clean tools post-struggle");
+    assert(recs[0].recovered_from === "tool_error_loop", "recovered_from set");
+  } finally { cleanup(home); }
+}
+
+function testRecoveryResetsOnError() {
+  const home = newTmpHome();
+  try {
+    for (let i = 0; i < 3; i++) {
+      feed(home, {
+        hook_event_name: "PostToolUse", session_id: "s1", cwd: "/x",
+        tool_name: "Bash",
+        tool_input: { command: `cmd ${i}` },
+        tool_response: { is_error: true, content: "error: failed" },
+      });
+    }
+    feed(home, { hook_event_name: "PostToolUse", session_id: "s1", cwd: "/x",
+      tool_name: "Read", tool_input: { file_path: "/tmp/a" }, tool_response: { content: "ok" } });
+    feed(home, { hook_event_name: "PostToolUse", session_id: "s1", cwd: "/x",
+      tool_name: "Read", tool_input: { file_path: "/tmp/b" }, tool_response: { content: "ok" } });
+    feed(home, { hook_event_name: "PostToolUse", session_id: "s1", cwd: "/x",
+      tool_name: "Bash", tool_input: { command: "x" }, tool_response: { is_error: true, content: "error: again" } });
+    feed(home, { hook_event_name: "PostToolUse", session_id: "s1", cwd: "/x",
+      tool_name: "Read", tool_input: { file_path: "/tmp/c" }, tool_response: { content: "ok" } });
+    const j = readJournal(home);
+    assert(j.filter(e => e.type === "clean_recovery").length === 0, "no clean_recovery when error breaks the streak");
+  } finally { cleanup(home); }
+}
+
+function testActiveSkillsPayload() {
+  const home = newTmpHome();
+  try {
+    feed(home, { hook_event_name: "PreToolUse", session_id: "s1", cwd: "/x",
+      tool_name: "Skill", tool_input: { skill: "my-skill" } });
+    for (let i = 0; i < 5; i++) {
+      feed(home, { hook_event_name: "UserPromptSubmit", session_id: "s1", cwd: "/x", prompt: "ok" });
+    }
+    const j = readJournal(home);
+    const s = j.find(e => e.type === "correction_free_streak");
+    assert(s && Array.isArray(s.active_skills) && s.active_skills.includes("my-skill"),
+      "correction_free_streak payload includes active skill");
+  } finally { cleanup(home); }
+}
+
+async function main() {
+  testCorrectionFreeStreak();
+  testStreakResetsOnSessionChange();
+  testCleanRecovery();
+  testRecoveryResetsOnError();
+  testActiveSkillsPayload();
+  console.log("all tests passed");
+}
+
+if (import.meta.url === `file://${process.argv[1]}`) main();

adam/tests/run-tests.sh

@@ -1,8 +1,23 @@
 #!/usr/bin/env bash
+# Test harness: ALWAYS runs against an isolated $HOME under mktemp.
+# The hook/nudge/archive scripts being tested are sourced from the real $HOME
+# but invoked with HOME="$TMP_HOME" so journal/state/usage write to the sandbox.
 set -euo pipefail
 
-ROOT="$HOME/.claude/adam"
-HOOK="$HOME/.claude/hooks/adam-observe.mjs"
+REAL_HOME="$HOME"
+HOOK="$REAL_HOME/.claude/hooks/adam-observe.mjs"
+NUDGE="$REAL_HOME/.claude/hooks/adam-nudge.mjs"
+ARCHIVE="$REAL_HOME/.claude/adam/scripts/adam-archive.mjs"
+
+TMP_HOME="$(mktemp -d -t adam-test.XXXXXX)"
+trap 'rm -rf "$TMP_HOME"' EXIT INT TERM
+mkdir -p "$TMP_HOME/.claude/adam/proposals" "$TMP_HOME/.claude/adam/applied" "$TMP_HOME/.claude/adam/rejected" "$TMP_HOME/.claude/adam/journal"
+
+ROOT="$TMP_HOME/.claude/adam"
+HOOK_RUN()    { HOME="$TMP_HOME" node "$HOOK" "$@"; }
+NUDGE_RUN()   { HOME="$TMP_HOME" node "$NUDGE" "$@"; }
+ARCHIVE_RUN() { HOME="$TMP_HOME" node "$ARCHIVE" "$@"; }
+
 PASS=0
 FAIL=0
 
@@ -40,7 +55,7 @@ assert_grep() {
 echo "Test 1: user correction"
 reset_state
 echo '{"hook_event_name":"UserPromptSubmit","prompt":"no, that is wrong","session_id":"s1","cwd":"/tmp/x"}' \
-  | node "$HOOK" >/dev/null 2>&1 || true
+  | HOOK_RUN >/dev/null 2>&1 || true
 assert_lines "$ROOT/journal.jsonl" 1 "correction creates journal entry"
 assert_grep  "$ROOT/journal.jsonl" '"type":"correction"' "entry has correct type"
 
@@ -49,7 +64,7 @@ echo "Test 2: retry loop"
 reset_state
 for i in 1 2 3; do
   echo '{"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"ls"},"session_id":"s1","cwd":"/tmp/x"}' \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 assert_grep "$ROOT/journal.jsonl" '"type":"retry_loop"' "3x same Bash logs retry_loop"
 
@@ -57,29 +72,29 @@ assert_grep "$ROOT/journal.jsonl" '"type":"retry_loop"' "3x same Bash logs retry
 echo "Test 3: usage counter"
 reset_state
 echo '{"hook_event_name":"PreToolUse","tool_name":"Skill","tool_input":{"skill":"foo"},"session_id":"s1","cwd":"/tmp/x"}' \
-  | node "$HOOK" >/dev/null 2>&1 || true
+  | HOOK_RUN >/dev/null 2>&1 || true
 assert_grep "$ROOT/usage.json" '"skill:foo"' "Skill invocation increments usage counter"
 
 # --- Test 3b: agent prefix in usage counter ---
 echo "Test 3b: agent prefix"
 reset_state
 echo '{"hook_event_name":"PreToolUse","tool_name":"Agent","tool_input":{"subagent_type":"bar"},"session_id":"s1","cwd":"/tmp/x"}' \
-  | node "$HOOK" >/dev/null 2>&1 || true
+  | HOOK_RUN >/dev/null 2>&1 || true
 assert_grep "$ROOT/usage.json" '"agent:bar"' "Agent invocation increments prefixed counter"
 
 # --- Test 4: weak agent ---
 echo "Test 4: weak agent"
 reset_state
 echo '{"hook_event_name":"PostToolUse","tool_name":"Agent","tool_input":{"subagent_type":"x"},"session_id":"s1","cwd":"/tmp/x"}' \
-  | node "$HOOK" >/dev/null 2>&1 || true
+  | HOOK_RUN >/dev/null 2>&1 || true
 echo '{"hook_event_name":"PostToolUse","tool_name":"Agent","tool_input":{"subagent_type":"x"},"session_id":"s1","cwd":"/tmp/x"}' \
-  | node "$HOOK" >/dev/null 2>&1 || true
+  | HOOK_RUN >/dev/null 2>&1 || true
 assert_grep "$ROOT/journal.jsonl" '"type":"weak_agent"' "2x same agent logs weak_agent"
 
 # --- Test 5: hook never blocks (exit 0) ---
 echo "Test 5: hook always exit 0 even on garbage input"
 reset_state
-if echo 'not json' | node "$HOOK" >/dev/null 2>&1; then
+if echo 'not json' | HOOK_RUN >/dev/null 2>&1; then
   echo "  PASS: garbage input exit 0"; PASS=$((PASS+1))
 else
   echo "  FAIL: garbage input non-zero exit"; FAIL=$((FAIL+1))
@@ -91,7 +106,7 @@ reset_state
 # Seed journal with > 5 MB to trigger rotation on next write
 head -c 5500000 /dev/urandom | base64 > "$ROOT/journal.jsonl"
 echo '{"hook_event_name":"UserPromptSubmit","prompt":"no, that is wrong","session_id":"s1","cwd":"/tmp/x"}' \
-  | node "$HOOK" >/dev/null 2>&1 || true
+  | HOOK_RUN >/dev/null 2>&1 || true
 rotated=$(ls "$ROOT/journal/" 2>/dev/null | wc -l | tr -d ' ')
 if [ "$rotated" -ge "1" ]; then
   echo "  PASS: journal rotated ($rotated archive present)"; PASS=$((PASS+1))
@@ -103,10 +118,9 @@ rm -f "$ROOT/journal/"*.jsonl 2>/dev/null
 
 # --- Test 7: nudge prints reminder when ≥3 proposals ---
 echo "Test 7: SessionStart nudge"
-NUDGE="$HOME/.claude/hooks/adam-nudge.mjs"
 rm -f "$ROOT/proposals/"*.md 2>/dev/null
-touch "$ROOT/proposals/a.md" "$ROOT/proposals/b.md" "$ROOT/proposals/c.md"
-out=$(echo '{"hook_event_name":"SessionStart"}' | node "$NUDGE" 2>&1 || true)
+touch "$ROOT/proposals/2026-05-10-001-memory-a.md" "$ROOT/proposals/2026-05-10-002-skill_new-b.md" "$ROOT/proposals/2026-05-10-003-skill_edit-c.md"
+out=$(echo '{"hook_event_name":"SessionStart"}' | NUDGE_RUN 2>&1 || true)
 if echo "$out" | grep -q "3 proposals queued"; then
   echo "  PASS: nudge prints reminder"; PASS=$((PASS+1))
 else
@@ -115,7 +129,7 @@ fi
 rm -f "$ROOT/proposals/"*.md
 
 echo "Test 8: nudge silent when 0 proposals"
-out=$(echo '{"hook_event_name":"SessionStart"}' | node "$NUDGE" 2>&1 || true)
+out=$(echo '{"hook_event_name":"SessionStart"}' | NUDGE_RUN 2>&1 || true)
 if [ -z "$out" ]; then
   echo "  PASS: nudge silent"; PASS=$((PASS+1))
 else
@@ -127,7 +141,7 @@ echo "Test 9: tool_error_loop on repeated identical error"
 reset_state
 for i in 1 2 3; do
   echo '{"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"foo"},"tool_response":{"is_error":true,"content":"Error: command not found: foo"},"session_id":"s9","cwd":"/tmp/x"}' \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 assert_grep "$ROOT/journal.jsonl" '"type":"tool_error_loop"' "3x same error logs tool_error_loop"
 
@@ -136,7 +150,7 @@ echo "Test 10: dead_end after 8 tools without UserPromptSubmit"
 reset_state
 for i in 1 2 3 4 5 6 7 8; do
   echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"Bash\",\"tool_input\":{\"command\":\"step$i\"},\"session_id\":\"s10\",\"cwd\":\"/tmp/x\"}" \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 assert_grep "$ROOT/journal.jsonl" '"type":"dead_end"' "8x PostToolUse without prompt logs dead_end"
 
@@ -145,13 +159,13 @@ echo "Test 11: dead_end counter resets on UserPromptSubmit"
 reset_state
 for i in 1 2 3 4 5 6 7; do
   echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"Bash\",\"tool_input\":{\"command\":\"step$i\"},\"session_id\":\"s11\",\"cwd\":\"/tmp/x\"}" \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 echo '{"hook_event_name":"UserPromptSubmit","prompt":"continue","session_id":"s11","cwd":"/tmp/x"}' \
-  | node "$HOOK" >/dev/null 2>&1 || true
+  | HOOK_RUN >/dev/null 2>&1 || true
 for i in 8 9 10 11 12; do
   echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"Bash\",\"tool_input\":{\"command\":\"step$i\"},\"session_id\":\"s11\",\"cwd\":\"/tmp/x\"}" \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 if grep -qE '"type":"dead_end"' "$ROOT/journal.jsonl"; then
   echo "  FAIL: dead_end fired despite reset"; FAIL=$((FAIL+1))
@@ -164,11 +178,11 @@ echo "Test 12: session change resets dead_end counter"
 reset_state
 for i in 1 2 3 4 5 6 7; do
   echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"Bash\",\"tool_input\":{\"command\":\"a$i\"},\"session_id\":\"sA\",\"cwd\":\"/tmp/x\"}" \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 # Now switch to session sB. First post-tool in new session should NOT trigger dead_end.
 echo '{"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"b1"},"session_id":"sB","cwd":"/tmp/x"}' \
-  | node "$HOOK" >/dev/null 2>&1 || true
+  | HOOK_RUN >/dev/null 2>&1 || true
 if grep -qE '"type":"dead_end"' "$ROOT/journal.jsonl"; then
   echo "  FAIL: dead_end fired across session boundary"; FAIL=$((FAIL+1))
 else
@@ -180,7 +194,7 @@ echo "Test 13: edit_churn fires after 4 edits to same file"
 reset_state
 for i in 1 2 3 4; do
   echo '{"hook_event_name":"PostToolUse","tool_name":"Edit","tool_input":{"file_path":"/tmp/x.py"},"session_id":"sE","cwd":"/tmp/x"}' \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 assert_grep "$ROOT/journal.jsonl" '"type":"edit_churn"' "4x edits to same file logs edit_churn"
 
@@ -189,7 +203,7 @@ echo "Test 14: build_loop fires after 2 failed builds"
 reset_state
 for i in 1 2; do
   echo '{"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"go test ./..."},"tool_response":{"is_error":true,"content":"FAIL: TestFoo"},"session_id":"sB","cwd":"/tmp/x"}' \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 assert_grep "$ROOT/journal.jsonl" '"type":"build_loop"' "2x failed test logs build_loop"
 
@@ -198,7 +212,7 @@ echo "Test 15: subagent_dispatch_pattern fires after 3 same-type dispatches"
 reset_state
 for i in 1 2 3; do
   echo '{"hook_event_name":"PreToolUse","tool_name":"Agent","tool_input":{"subagent_type":"orchestrator"},"session_id":"sD","cwd":"/tmp/x"}' \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 assert_grep "$ROOT/journal.jsonl" '"type":"subagent_dispatch_pattern"' "3x same subagent logs subagent_dispatch_pattern"
 
@@ -207,7 +221,7 @@ echo "Test 16: build_loop ignores non-build commands"
 reset_state
 for i in 1 2 3; do
   echo '{"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"ls /nope"},"tool_response":{"is_error":true,"content":"No such file"},"session_id":"sN","cwd":"/tmp/x"}' \
-    | node "$HOOK" >/dev/null 2>&1 || true
+    | HOOK_RUN >/dev/null 2>&1 || true
 done
 if grep -qE '"type":"build_loop"' "$ROOT/journal.jsonl"; then
   echo "  FAIL: build_loop fired on non-build command"; FAIL=$((FAIL+1))
@@ -215,6 +229,183 @@ else
   echo "  PASS: build_loop correctly ignored non-build command"; PASS=$((PASS+1))
 fi
 
+# --- Test 17: adam-archive moves matching entries to actioned file ---
+echo "Test 17: adam-archive moves matching journal entries"
+reset_state
+rm -f "$ROOT/journal/actioned-test-archive-001.jsonl"
+cat > "$ROOT/journal.jsonl" <<EOF
+{"ts":"2026-01-01T00:00:00Z","session":"sX","type":"correction"}
+{"ts":"2026-01-02T00:00:00Z","session":"sX","type":"correction"}
+{"ts":"2026-01-03T00:00:00Z","session":"sX","type":"dead_end"}
+EOF
+mkdir -p /tmp/adam-test-17
+cat > /tmp/adam-test-17/proposal.md <<EOF
+---
+id: test-archive-001
+type: memory
+target: /tmp/test
+confidence: 5
+blast_radius: low
+auto_apply_eligible: false
+status: applied
+source_entries:
+  - "2026-01-01T00:00:00Z"
+  - "2026-01-02T00:00:00Z"
+---
+# Why
+test
+EOF
+ARCHIVE_RUN /tmp/adam-test-17/proposal.md >/dev/null 2>&1 || true
+remaining=$(wc -l < "$ROOT/journal.jsonl" | tr -d ' ')
+archived=$(wc -l < "$ROOT/journal/actioned-test-archive-001.jsonl" 2>/dev/null | tr -d ' ' || echo 0)
+if [ "$remaining" = "1" ] && [ "$archived" = "2" ]; then
+  echo "  PASS: archive moved 2 matching, kept 1 unmatched"; PASS=$((PASS+1))
+else
+  echo "  FAIL: expected 1 remaining + 2 archived, got $remaining + $archived"; FAIL=$((FAIL+1))
+fi
+rm -rf /tmp/adam-test-17 "$ROOT/journal/actioned-test-archive-001.jsonl"
+
+# --- Test 18: adam-archive no-op when source_entries missing ---
+echo "Test 18: adam-archive no-op when source_entries missing"
+reset_state
+echo '{"ts":"2026-01-01T00:00:00Z","type":"correction"}' > "$ROOT/journal.jsonl"
+mkdir -p /tmp/adam-test-18
+cat > /tmp/adam-test-18/proposal.md <<EOF
+---
+id: test-noop-002
+type: memory
+---
+# Why
+no source_entries
+EOF
+ARCHIVE_RUN /tmp/adam-test-18/proposal.md >/dev/null 2>&1 || true
+if [ -f "$ROOT/journal/actioned-test-noop-002.jsonl" ]; then
+  echo "  FAIL: archive file created when no source_entries"; FAIL=$((FAIL+1))
+else
+  echo "  PASS: no archive file created"; PASS=$((PASS+1))
+fi
+remaining=$(wc -l < "$ROOT/journal.jsonl" | tr -d ' ')
+if [ "$remaining" = "1" ]; then
+  echo "  PASS: journal unchanged"; PASS=$((PASS+1))
+else
+  echo "  FAIL: journal modified ($remaining lines, expected 1)"; FAIL=$((FAIL+1))
+fi
+rm -rf /tmp/adam-test-18
+
+# --- Test 19: correction_free_streak fires after 5 clean prompts ---
+echo "Test 19: correction_free_streak after 5 clean prompts"
+reset_state
+for i in 1 2 3 4 5; do
+  echo "{\"hook_event_name\":\"UserPromptSubmit\",\"prompt\":\"please do step $i\",\"session_id\":\"sCF\",\"cwd\":\"/tmp/x\"}" \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+assert_grep "$ROOT/journal.jsonl" '"type":"correction_free_streak"' "5 clean prompts logs correction_free_streak"
+
+# --- Test 20: correction phrase resets streak counter ---
+echo "Test 20: correction phrase breaks correction_free_streak"
+reset_state
+for i in 1 2 3 4; do
+  echo "{\"hook_event_name\":\"UserPromptSubmit\",\"prompt\":\"please do step $i\",\"session_id\":\"sCB\",\"cwd\":\"/tmp/x\"}" \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+echo '{"hook_event_name":"UserPromptSubmit","prompt":"no, undo that","session_id":"sCB","cwd":"/tmp/x"}' \
+  | HOOK_RUN >/dev/null 2>&1 || true
+echo '{"hook_event_name":"UserPromptSubmit","prompt":"go on","session_id":"sCB","cwd":"/tmp/x"}' \
+  | HOOK_RUN >/dev/null 2>&1 || true
+if grep -qE '"type":"correction_free_streak"' "$ROOT/journal.jsonl"; then
+  echo "  FAIL: correction_free_streak fired despite intervening correction"; FAIL=$((FAIL+1))
+else
+  echo "  PASS: correction phrase reset the streak counter"; PASS=$((PASS+1))
+fi
+
+# --- Test 21: clean_recovery fires after struggle + 3 clean tools ---
+echo "Test 21: clean_recovery after struggle + 3 clean tools"
+reset_state
+for i in 1 2 3; do
+  echo '{"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"foo"},"tool_response":{"is_error":true,"content":"Error: command not found: foo"},"session_id":"sR","cwd":"/tmp/x"}' \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+for i in 1 2 3; do
+  echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"Read\",\"tool_input\":{\"file_path\":\"/tmp/ok-$i\"},\"tool_response\":{\"content\":\"ok\"},\"session_id\":\"sR\",\"cwd\":\"/tmp/x\"}" \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+assert_grep "$ROOT/journal.jsonl" '"type":"clean_recovery"' "3 clean tools after struggle logs clean_recovery"
+assert_grep "$ROOT/journal.jsonl" '"recovered_from":"tool_error_loop"' "recovered_from set on clean_recovery"
+
+# --- Test 22: clean_recovery resets when error breaks the streak ---
+echo "Test 22: clean_recovery suppressed by intervening error"
+reset_state
+for i in 1 2 3; do
+  echo '{"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"foo"},"tool_response":{"is_error":true,"content":"Error: command not found: foo"},"session_id":"sRE","cwd":"/tmp/x"}' \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+for i in 1 2; do
+  echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"Read\",\"tool_input\":{\"file_path\":\"/tmp/ok-$i\"},\"tool_response\":{\"content\":\"ok\"},\"session_id\":\"sRE\",\"cwd\":\"/tmp/x\"}" \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+echo '{"hook_event_name":"PostToolUse","tool_name":"Bash","tool_input":{"command":"x"},"tool_response":{"is_error":true,"content":"Error: again"},"session_id":"sRE","cwd":"/tmp/x"}' \
+  | HOOK_RUN >/dev/null 2>&1 || true
+echo '{"hook_event_name":"PostToolUse","tool_name":"Read","tool_input":{"file_path":"/tmp/ok-3"},"tool_response":{"content":"ok"},"session_id":"sRE","cwd":"/tmp/x"}' \
+  | HOOK_RUN >/dev/null 2>&1 || true
+if grep -qE '"type":"clean_recovery"' "$ROOT/journal.jsonl"; then
+  echo "  FAIL: clean_recovery fired despite intervening error"; FAIL=$((FAIL+1))
+else
+  echo "  PASS: clean_recovery suppressed by intervening error"; PASS=$((PASS+1))
+fi
+
+# --- Test 23: active_skills payload populated on win signals ---
+echo "Test 23: correction_free_streak payload includes active skill"
+reset_state
+echo '{"hook_event_name":"PreToolUse","tool_name":"Skill","tool_input":{"skill":"caveman"},"session_id":"sAS","cwd":"/tmp/x"}' \
+  | HOOK_RUN >/dev/null 2>&1 || true
+for i in 1 2 3 4 5; do
+  echo "{\"hook_event_name\":\"UserPromptSubmit\",\"prompt\":\"step $i\",\"session_id\":\"sAS\",\"cwd\":\"/tmp/x\"}" \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+assert_grep "$ROOT/journal.jsonl" '"active_skills":\["caveman"\]' "active_skills payload includes invoked skill"
+
+# --- Test 24: task_completed fires on diverse multi-tool task ---
+echo "Test 24: task_completed after 5 tools / 3 kinds / no corrections"
+reset_state
+for kind in Bash Read Edit Write Grep; do
+  echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"$kind\",\"tool_input\":{},\"session_id\":\"sT\",\"cwd\":\"/tmp/x\"}" \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+echo '{"hook_event_name":"UserPromptSubmit","prompt":"go on","session_id":"sT","cwd":"/tmp/x"}' \
+  | HOOK_RUN >/dev/null 2>&1 || true
+assert_grep "$ROOT/journal.jsonl" '"type":"task_completed"' "5 tools + 5 kinds + 0 corrections emits task_completed"
+
+# --- Test 25: task_completed suppressed when tool diversity < 3 ---
+echo "Test 25: task_completed suppressed on single-tool run"
+reset_state
+for i in 1 2 3 4 5; do
+  echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"Edit\",\"tool_input\":{\"file_path\":\"/tmp/$i\"},\"session_id\":\"sT2\",\"cwd\":\"/tmp/x\"}" \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+echo '{"hook_event_name":"UserPromptSubmit","prompt":"go on","session_id":"sT2","cwd":"/tmp/x"}' \
+  | HOOK_RUN >/dev/null 2>&1 || true
+if grep -qE '"type":"task_completed"' "$ROOT/journal.jsonl"; then
+  echo "  FAIL: task_completed fired on single-tool task"; FAIL=$((FAIL+1))
+else
+  echo "  PASS: task_completed suppressed (low tool diversity)"; PASS=$((PASS+1))
+fi
+
+# --- Test 26: task_completed suppressed when correction fires mid-task ---
+echo "Test 26: task_completed suppressed after correction"
+reset_state
+for kind in Bash Read Edit Write Grep; do
+  echo "{\"hook_event_name\":\"PostToolUse\",\"tool_name\":\"$kind\",\"tool_input\":{},\"session_id\":\"sT3\",\"cwd\":\"/tmp/x\"}" \
+    | HOOK_RUN >/dev/null 2>&1 || true
+done
+# Correction phrase resets task_corrections inside the same UserPromptSubmit cycle, so the prior run is disqualified.
+echo '{"hook_event_name":"UserPromptSubmit","prompt":"no, undo that","session_id":"sT3","cwd":"/tmp/x"}' \
+  | HOOK_RUN >/dev/null 2>&1 || true
+if grep -qE '"type":"task_completed"' "$ROOT/journal.jsonl"; then
+  echo "  FAIL: task_completed fired despite correction on the closing prompt"; FAIL=$((FAIL+1))
+else
+  echo "  PASS: task_completed suppressed by correction"; PASS=$((PASS+1))
+fi
+
 echo
 echo "Results: $PASS passed, $FAIL failed"
 [ "$FAIL" = "0" ]

agents/adam.md

@@ -18,16 +18,9 @@ You MUST obey these on every proposal:
 4. **Verifiable success criterion** — every proposal has a `# Success criterion` section describing a runnable check.
 5. **Naive then optimize** — first proposal for a pattern is the boring obvious solution.
 
-## Inputs (passed in dispatch prompt)
+## Inputs
 
-- `journal_path`: `~/.claude/adam/journal.jsonl`
-- `state_path`: `~/.claude/adam/state.json` (cursor)
-- `usage_path`: `~/.claude/adam/usage.json`
-- `proposals_dir`: `~/.claude/adam/proposals/`
-- `applied_dir`: `~/.claude/adam/applied/`
-- `rejected_dir`: `~/.claude/adam/rejected/`
-- `transcripts_root`: `~/.claude/projects/`
-- `skills_root`: `~/.claude/skills/`
+Paths arrive via the dispatch prompt — see `~/.claude/skills/adam-self-improvement/SKILL.md` §1.
 
 ## Signal types
 
@@ -43,20 +36,24 @@ The hook emits these `type` values into the journal:
 | `edit_churn` | same file edited 4× in window | file basename |
 | `build_loop` | 2 build/test/compile commands fail in session | session |
 | `subagent_dispatch_pattern` | same subagent dispatched ≥3× cumulatively | subagent_type |
+| `correction_free_streak` | 5 clean UserPromptSubmits in a row (no correction phrase) | `active_skills[0]` |
+| `clean_recovery` | 3 clean PostToolUse events after a `tool_error_loop`/`dead_end`/`retry_loop` | (`recovered_from`, `active_skills[0]`) |
+| `task_completed` | UserPromptSubmit closes a run of ≥5 tool calls with ≥3 distinct tool kinds and 0 corrections | sorted `tool_kinds` tuple |
 
 ## Process
 
-1. Read `state.json` → `cursor` (number of journal lines already processed).
-2. Read `journal.jsonl`. New observations = lines after `cursor`.
-3. If 0 new lines, emit punch list `{"new":0}` and stop.
-4. **Build feedback context** (run once per `/reflect`):
-   a. List `rejected_dir/` filenames. Parse each `# Why` and `# Reason` sections. Build a set of rejected ideas (token-tokenized for similarity matching).
-   b. List `applied_dir/` filenames. Parse frontmatter `type` and `target`. Tally `applied_by_type[type]` and `applied_by_target[basename(target)]`.
-   c. From these, compute **type biases**:
+1. **Build feedback context** (run once per `/reflect`):
+   a. List `rejected_dir/` filenames. Parse each frontmatter `source_entries` (if present), `# Why` and `# Reason` sections.
+   b. List `applied_dir/` filenames. Parse each frontmatter `type`, `target`, `source_entries`. Tally `applied_by_type[type]`.
+   c. Compute the **excluded-timestamps set**: union of all `source_entries` arrays across `applied_dir/` + `rejected_dir/`. Journal entries with these `ts` values have already been actioned and MUST NOT be re-clustered.
+   d. Build the **rejected-ideas set** (token-tokenized `# Why` content) for fuzzy fallback matching when a new cluster topic resembles a rejected one but doesn't share `source_entries` (handles legacy proposals without `source_entries`).
+   e. Compute **type biases**:
       - Types with applied:rejected ratio >2:1 (over ≥3 total): neutral, no bonus.
       - Types with applied:rejected ratio <1:2 (over ≥3 rejections): **-1 confidence penalty**, recorded in proposal `# Why` as "type-bias-penalty: <reason>".
-5. Cluster new observations:
-   - `correction`: tokenize phrase (drop stopwords, keep content tokens). Phrases sharing ≥2 content tokens collapse into one cluster — regardless of `prev_tool` or `cwd`. Record distinct cwds in cluster (used for CLAUDE.md eligibility).
+2. Read `journal.jsonl`. Filter out entries whose `ts` is in the excluded-timestamps set. The result = **active observations**.
+3. If 0 active observations, emit punch list `{"new":0}` and stop.
+4. Cluster active observations:
+   - `correction`: tokenize phrase (drop stopwords, keep content tokens). Phrases sharing ≥2 content tokens collapse into one cluster — regardless of `prev_tool` or `cwd`. Record distinct cwds (used for CLAUDE.md eligibility).
    - `retry_loop`: cluster by `tool`.
    - `weak_agent`: cluster by `subagent_type`.
    - `tool_error_loop`: cluster by `fp`.
@@ -64,26 +61,30 @@ The hook emits these `type` values into the journal:
    - `edit_churn`: cluster by file basename pattern (e.g. `*.test.ts`).
    - `build_loop`: cluster by `session`.
    - `subagent_dispatch_pattern`: cluster by `subagent_type`.
-6. **Multi-axis correlation**: for each session that produced ≥2 distinct struggle types (`tool_error_loop`, `dead_end`, `weak_agent`, `retry_loop`, `edit_churn`, `build_loop`), tag clusters from that session as `multi_axis: true`. This grants +1 confidence at scoring.
-7. For each cluster qualifying under the rubric — ≥3× across ≥2 sessions, OR ≥3× within a single session for struggle types, OR (for `correction`) ≥3 occurrences across ≥2 cwds:
-   a. If cluster topic matches a rejected idea (≥2 token overlap with rejection's `# Why`), skip with reason `"rejected-similar"`.
+   - `correction_free_streak`: cluster by `active_skills[0]`. Treat ≥3 streaks across ≥2 sessions naming the same skill as cross-session evidence.
+   - `clean_recovery`: cluster by (`recovered_from`, `active_skills[0]`). A win cluster qualifies for `skill_edit` only when the named skill exists in `skills_root`.
+   - `task_completed`: cluster by sorted `tool_kinds` tuple (the multi-tool recipe). Single entry qualifies for `skill_new` proposal (drafting protocol applies). Cross-session evidence requires ≥2 entries from distinct sessions with same tuple — without it, proposal queues, never auto-applies. Run the existing skill-overlap rule before drafting: if the recipe matches an existing skill's name/description tokens, route to `skill_edit` instead.
+5. **Multi-axis correlation**: for each session that produced ≥2 distinct struggle types (`tool_error_loop`, `dead_end`, `weak_agent`, `retry_loop`, `edit_churn`, `build_loop`), tag clusters from that session as `multi_axis: true`. This grants +1 confidence at scoring.
+6. For each cluster qualifying under the rubric — ≥3 occurrences across ≥2 sessions, OR (for struggle types) ≥1 entry within a single session, OR (for `correction`) ≥3 occurrences across ≥2 cwds:
+   a. If cluster topic matches a rejected idea via the rejected-ideas fuzzy set (≥2 token overlap with rejection's `# Why`), skip with reason `"rejected-similar"`.
    b. Pull ~20 messages of transcript context from `transcripts_root` to enrich. Never read full transcripts.
-   c. **Solution synthesis** (when type would be `skill_new` AND cluster qualifies for proposal): pull additional ~30 messages of transcript window around the friction events (~50 messages total). Extract:
+   b1. **Causal diagnosis** (required for every proposal type): from the pulled context, draft a `# Diagnosis` block per the "Diagnosis drafting protocol". Cite ≥1 verbatim transcript quote within the `source_entries` window. If causation cannot be reconstructed, write `Mismatch: unclear` and apply `-1` confidence (rubric penalty). Diagnosis writes the proposal's narrative *before* the proposal body is drafted in step 6e.
+   c. **Solution synthesis** (when candidate type is `skill_new` AND cluster qualifies): pull additional ~30 messages around friction events (~50 messages total). Extract:
       - Concrete trigger phrases the user says verbatim.
       - Tools / files involved.
       - Successful resolution patterns later in transcript (positive endorsement).
       - Counterexamples (false-positive triggers to exclude).
-   d. **Skill overlap check** (skill_new candidates only): see "Skill overlap rule" below. If overlap qualifies, switch type to `skill_edit` targeting the matched SKILL.md.
+   d. **Skill overlap check** (`skill_new` only): see "Skill overlap rule". If overlap qualifies, switch type to `skill_edit` targeting matched SKILL.md.
    e. **Draft full content**:
-      - `skill_new`: draft the complete SKILL.md per "Skill drafting protocol" below. `# Proposed change` contains the full file body.
-      - `skill_edit`: draft an append-only unified diff per "Skill overlap rule".
-      - `memory`: draft full memory file content (frontmatter + body).
-      - Other types: per existing rules (unified diff or full content).
+      - `skill_new`: complete SKILL.md per "Skill drafting protocol".
+      - `skill_edit`: append-only unified diff per "Skill overlap rule".
+      - `memory`: complete memory file per "Memory drafting protocol".
+      - Other: per existing rules (unified diff or full content).
    f. Score against rubric → `confidence`, `blast_radius`, `cross_session_evidence`, `multi_axis`, `auto_apply_eligible`.
-   g. Apply feedback bias (step 4c) and multi-axis bonus.
-   h. Emit proposal file to `proposals_dir/`.
-8. Update `cursor` in `state.json` to new line count.
-9. Emit punch list to stdout (last message): `{"new":N, "high_confidence":[...], "queued":[...], "skipped":[...]}`.
+   g. Apply feedback bias (step 1e) and multi-axis bonus.
+   h. **Record `source_entries`**: list every journal entry timestamp that fed this cluster. Goes in proposal frontmatter as a YAML block-form array (one `- "<ts>"` per line). The skill consumes this on apply/reject to archive matching entries out of `journal.jsonl` and into `journal/actioned-<id>.jsonl`.
+   i. Emit proposal file to `proposals_dir/`.
+7. Emit punch list to stdout (last message): `{"new":N, "high_confidence":[...], "queued":[...], "skipped":[...]}`.
 
 ## Skill overlap rule
 
@@ -138,38 +139,124 @@ Constraints:
 - ≤80 lines of body content. Karpathy "Surgical".
 - Slug MUST NOT collide with any existing skill name in `skills_root`.
 
-When the main thread applies a `skill_new` proposal:
-1. Creates `~/.claude/skills/<slug>/` directory.
-2. Writes the `# Proposed change` body to `<slug>/SKILL.md`.
-3. Tells the user: "skill `<slug>` written. Activates immediately on next user turn (CC v2.1.0+ auto-hot-reload)."
+
+## Memory drafting protocol (for `memory` proposals)
+
+Every `memory` proposal's `# Proposed change` section MUST contain the COMPLETE memory file body — frontmatter + content — that will be written to the target path under `~/.claude/projects/<encoded-home>/memory/<slug>.md`.
+
+Required structure:
+
+```markdown
+---
+name: <human-readable name, ≤80 chars>
+description: <one-line description used to decide future relevance — be specific, ≤200 chars>
+type: user | feedback | project | reference
+originSessionId: <session_id from journal entries that fed this cluster>
+---
+
+<Body content per type, see CLAUDE.md memory schema:
+  - feedback: lead with the rule, then **Why:** line, then **How to apply:** line.
+  - project: lead with fact/decision, then **Why:** and **How to apply:** lines.
+  - user: brief description of role/preference/knowledge.
+  - reference: pointer to external system + what's there.>
+```
+
+Constraints:
+- Frontmatter fields `name`, `description`, `type` are **required**. Skill enforces this at apply time.
+- `originSessionId` is required — must be a `session` value from one of the cluster's journal entries.
+- ≤50 LOC of body content. Surgical.
+- Slug (used in `target` path filename) must not collide with any existing memory file.
+- For `type=feedback` and `type=project`, body MUST contain `**Why:**` and `**How to apply:**` lines (CLAUDE.md memory schema).
+
+## Diagnosis drafting protocol (required for every proposal)
+
+Every proposal's body MUST include a `# Diagnosis` section between `# Why` and `# Assumptions`. It states the causal chain — *trigger → action → mismatch → outcome* — that motivates the proposed change, grounded in transcript evidence.
+
+Required structure (exactly four labelled lines):
+
+```markdown
+# Diagnosis
+
+**Trigger:** <what the user wanted / context the assistant was in — 1 sentence>
+**Action:** <what the assistant did — 1 sentence, name specific tools/files when relevant>
+**Mismatch:** <how the action diverged from the trigger — 1 sentence>
+**Outcome:** <what surfaced the mismatch — user correction quote, error message, dead end — must include ≥1 verbatim quote ≤80 chars from transcript, in backticks>
+```
+
+Constraints:
+
+1. ≤5 LOC of prose total.
+2. ≥1 verbatim transcript quote, max 80 chars, wrapped in backticks.
+3. The quote MUST appear within ~20 messages of one of the `source_entries` timestamps (transcript context window already pulled in step 6b).
+4. No speculation — if causation is unclear from available context, write `Mismatch: unclear — see Outcome` and the cluster takes a `-1` rubric penalty (see rubric).
+5. For win clusters (`correction_free_streak`, `clean_recovery`) where there is no failure: `Mismatch: None` is a valid value. Outcome cites the recovery quote or the silence ("no correction across N prompts" + closest journal `ts`).
+
+Example — struggle cluster:
+
+```markdown
+# Diagnosis
+
+**Trigger:** User asked to run Go tests in three different sessions, expected fresh results each time.
+**Action:** Assistant ran `go test ./...` without `-count=1` flag.
+**Mismatch:** Go's test cache returned stale passes from prior runs; assistant did not invalidate.
+**Outcome:** User corrected with `"no use go test -count=1"` (s-aaa, 2026-05-10T10:00).
+```
+
+Example — win cluster:
+
+```markdown
+# Diagnosis
+
+**Trigger:** Bash commands failed 3× with the same fingerprint; user did not intervene.
+**Action:** Assistant switched from Bash to `Read` + `Edit` for the same goal, finished without further error.
+**Mismatch:** None — recovery confirms the alternate tool is the right path here.
+**Outcome:** Three clean PostToolUse events after the loop (`recovered_from: tool_error_loop`, s-bbb).
+```
+
+After drafting the four lines, set proposal frontmatter `diagnosis_summary` to a single sentence ≤120 chars derived from the **Mismatch** line — used for skim/search across `applied/` and `rejected/`.
+
+## Win-driven `skill_edit` eligibility
+
+A `skill_edit` proposal sets `auto_apply_eligible: true` ONLY when ALL hold:
+
+1. `confidence ≥ 4`.
+2. `cross_session_evidence == true`.
+3. `# Why` cites ≥1 win-signal entry (`clean_recovery` or `correction_free_streak`) whose `active_skills` includes the target skill slug. Record this entry's `ts` in frontmatter field `win_evidence`.
+4. Diff is append-only — verify no `-` lines on existing SKILL.md content.
+5. Diff `+` lines ≤ 30.
+6. Resulting SKILL.md size ≤ 2× current size. Record both byte counts in frontmatter fields `bytes_before`, `bytes_after`.
+7. No entry in `applied_dir/` for the same `target` with `last_auto_edit` newer than 7 days ago (cooldown).
+8. No entry in `rejected_dir/` for this `target` with `auto_apply_blacklist: true` newer than 30 days ago.
+9. **Contradiction check passes.** Tokenize both the existing SKILL.md and the new appended section per the same tokenizer + stopword list as the skill-overlap rule. Search for negation tokens (`never`, `not`, `no`, `don't`, `avoid`, `forbid`, `stop`, `disable`) in the existing content; take a 6-token window around each match. If the new section contains an assertion token (`always`, `must`, `should`, `do`, `enable`, `yes`) whose surrounding 6-token window shares ≥2 content tokens with the existing negation window → flag as contradiction. Repeat in the inverse direction (negations in new section vs assertions in existing). On any flag: set `auto_apply_eligible: false` and add frontmatter field `contradiction_flag: "<one-line summary naming the negation token, the conflicting tokens, and the line in existing content where the negation appears>"`. Heuristic only — false positives queue for review, never silently auto-apply.
+
+If any of (3)–(9) fails: still emit the proposal, but `auto_apply_eligible: false` — main thread queues for review.
 
 ## Confidence rubric (deterministic — do NOT vibe)
 
 Sum:
 - Signal repeated ≥3× across ≥2 sessions: **+2**
-- Struggle signal (`tool_error_loop`, `dead_end`, `weak_agent`, `retry_loop`, `edit_churn`, `build_loop`) repeated ≥3× within a single session: **+2** *(does not stack with the cross-session bonus — pick whichever applies, never both)*
+- Struggle signal (`tool_error_loop`, `dead_end`, `weak_agent`, `retry_loop`, `edit_churn`, `build_loop`) appearing ≥1× within a single session: **+2** *(each struggle entry already represents a hook-side threshold crossing — e.g. 8 tools without a prompt, 3 same-args retries, 4 edits to one file. Treat each entry as one piece of evidence. Does not stack with the cross-session bonus.)*
 - Transcript contains positive endorsement (`yes`, `exactly`, `do that`, `keep doing`) within 2 messages of related action: **+2**
 - Multi-axis cluster (≥2 distinct struggle types in same session): **+1**
 - Type-bias penalty from feedback loop (≥3 rejections, applied:rejected ratio <1:2 for this `type`): **-1**
-- Blast radius low (memory file or new isolated skill): **+1**
-- Blast radius medium (new agent, new hook, edit existing skill): **0**
-- Blast radius high (CLAUDE.md, settings.json hooks, edit agent, deletion): **-1**
+- Diagnosis flags `Mismatch: unclear` (causation could not be reconstructed from transcript context): **-1**
+- Blast radius: low **+1**, medium **0**, high **-1** (default per type — see Proposal types table)
 - Surgical (one file, ≤50 LOC for non-skill_new; ≤80 LOC for skill_new): **+1**
 - Touches deny-list (settings.json hooks/permissions, CLAUDE.md, deletions): **-3**
 
 `auto_apply_eligible: true` requires **all** of:
 - `confidence ≥ 4`
 - `blast_radius == "low"`
-- `type ∈ {memory, skill_new}`
+- `type ∈ {memory, skill_new, skill_edit}` — `skill_edit` additionally requires the win-driven gate (see "Win-driven `skill_edit` eligibility")
 - `cross_session_evidence == true` — the +2 signal-repetition bonus came from the cross-session bullet (≥3× across ≥2 sessions). **Single-session-only struggle proposals always queue, never auto-apply, regardless of total confidence.** Record as frontmatter field `cross_session_evidence: true|false` on every proposal.
 
 ## Proposal types
 
 | Type | Target | Default blast | Auto-apply? |
 |---|---|---|---|
-| `memory` | `~/.claude/projects/<encoded-home>/memory/*.md` | low | yes if conf≥4 AND cross_session |
+| `memory` | `~/.claude/projects/-Users-nvm/memory/*.md` | low | yes if conf≥4 AND cross_session |
 | `skill_new` | new dir under `~/.claude/skills/` | low | yes if conf≥4 AND cross_session |
-| `skill_edit` | existing skill file | medium | no |
+| `skill_edit` | existing skill file | medium | yes if win-evidence + LOC + cooldown gates all pass (see "Win-driven skill_edit eligibility") |
 | `agent_new` | new file under `~/.claude/agents/` | medium | no |
 | `agent_edit` | existing agent file | medium | no |
 | `claude_md_edit` | `~/.claude/CLAUDE.md` | high | no |
@@ -210,11 +297,26 @@ cross_session_evidence: true | false
 multi_axis: true | false
 auto_apply_eligible: true | false
 status: queued
+source_entries:
+  - "<journal entry ts that fed this cluster>"
+  - "<another ts>"
+  - "..."
+# skill_edit only — required when auto_apply_eligible: true
+win_evidence: "<ts of triggering clean_recovery or correction_free_streak entry>"
+bytes_before: <int>
+bytes_after: <int>
+# skill_edit only — populated when contradiction heuristic flags a conflict (sets auto_apply_eligible: false)
+contradiction_flag: "<one-line summary or null>"
+# optional — auto-populated from Diagnosis Mismatch line
+diagnosis_summary: "<≤120 chars, single sentence>"
 ---
 
 # Why
 <observed evidence: session ids, dates, quotes from transcript synthesis>
 
+# Diagnosis
+<four labelled lines per "Diagnosis drafting protocol": Trigger / Action / Mismatch / Outcome — Outcome must contain ≥1 backtick-wrapped transcript quote ≤80 chars>
+
 # Assumptions
 - <assumption 1>
 - <assumption 2>
@@ -225,8 +327,8 @@ status: queued
 <for memory: full memory file body (frontmatter + content)>
 <for others: unified diff or full file content; for deletion: soft-delete command>
 
-# Overlap   (skill_edit only)
-<existing skill id, rule matched (name|description), overlapping tokens>
+# Overlap
+<conditional — see Skill overlap rule §6: only emitted for `skill_edit` proposals>
 
 # Success criterion
 <runnable check>
@@ -244,11 +346,8 @@ Print a single JSON line to stdout:
 
 ## What you must NOT do
 
-- Do not read full transcripts — ~20 messages base context per cluster, +30 for skill_new solution synthesis (50 total cap).
 - Do not call other agents.
 - Do not write to `~/.claude/skills/`, `~/.claude/agents/`, `settings.json`, `CLAUDE.md`, or any existing skill/agent file directly. All changes go through proposal files for main-thread review and apply.
 - Do not delete files. Deletion proposals describe a soft-move; the main thread executes it.
 - Do not write outside `proposals_dir/` and `state_path`.
-- Do not propose anything matching a `rejected/` entry (≥2 token overlap with rejection's `# Why`).
 - Do not invent trigger phrases for `skill_new` — every trigger must come from observed user input.
-- Do not stack the cross-session and single-session repetition bonuses — pick whichever qualifies, never both.

hooks/adam-nudge.mjs

@@ -7,7 +7,8 @@ const PROPOSALS = join(homedir(), ".claude", "adam", "proposals");
 const THRESHOLD = 3;
 
 try {
-  const files = readdirSync(PROPOSALS).filter(f => f.endsWith(".md"));
+  const PROPOSAL_RE = /^\d{4}-\d{2}-\d{2}-\d{3}-/;
+  const files = readdirSync(PROPOSALS).filter(f => PROPOSAL_RE.test(f) && f.endsWith(".md"));
   if (files.length >= THRESHOLD) {
     process.stdout.write(`adam: ${files.length} proposals queued. Run /reflect to review.\n`);
   }

hooks/adam-observe.mjs

@@ -28,6 +28,12 @@ const DEAD_END_THRESHOLD = 8;
 const EDIT_CHURN_THRESHOLD = 4;
 const BUILD_LOOP_THRESHOLD = 2;
 const SUBAGENT_DISPATCH_THRESHOLD = 3;
+const CORRECTION_FREE_THRESHOLD = 5;
+const CLEAN_RECOVERY_WINDOW = 3;
+const STRUGGLE_TYPES = new Set(["tool_error_loop", "dead_end", "retry_loop"]);
+const ACTIVE_SKILLS_LOOKBACK = 10;
+const TASK_TOOL_MIN = 5;
+const TASK_DIVERSITY_MIN = 3;
 const STATE_MAX_BYTES = 1_000_000;
 
 function safeRead(path, fallback) {
@@ -77,6 +83,17 @@ function readUsage(name) {
   return usage[name] || 0;
 }
 
+function pushActivity(state, kind, name, ts) {
+  state.activity_ring.push({ kind, name, ts });
+  if (state.activity_ring.length > ACTIVE_SKILLS_LOOKBACK) state.activity_ring.shift();
+}
+
+function activeNames(state, kind) {
+  const seen = new Set();
+  for (const e of state.activity_ring) if (e.kind === kind) seen.add(e.name);
+  return [...seen];
+}
+
 function errorFingerprint(toolResponse) {
   if (!toolResponse) return null;
   let text = "";
@@ -90,7 +107,8 @@ function errorFingerprint(toolResponse) {
   }
   if (!text) return null;
   text = text.slice(0, 4000);
-  const isError = (toolResponse && toolResponse.is_error === true) || ERROR_RE.test(text);
+  const isError = toolResponse.is_error === true ||
+    (toolResponse.is_error === undefined && ERROR_RE.test(text));
   if (!isError) return null;
   const m = text.match(ERROR_RE);
   const idx = m && typeof m.index === "number" ? m.index : 0;
@@ -114,6 +132,12 @@ function resetSessionLocal(state) {
   resetFrictionCounters(state);
   state.session_subagents = {};
   state.subagent_dispatch_emitted = {};
+  state.correctionFreeCounter = 0;
+  state.recoveryWatch = null;
+  state.tool_window = [];
+  state.task_tool_kinds = {};
+  state.task_tool_count = 0;
+  state.task_corrections = 0;
 }
 
 function ensureStateDefaults(state) {
@@ -127,6 +151,12 @@ function ensureStateDefaults(state) {
   if (typeof state.build_loop_emitted !== "boolean") state.build_loop_emitted = false;
   if (!state.session_subagents || typeof state.session_subagents !== "object") state.session_subagents = {};
   if (!state.subagent_dispatch_emitted || typeof state.subagent_dispatch_emitted !== "object") state.subagent_dispatch_emitted = {};
+  if (typeof state.correctionFreeCounter !== "number") state.correctionFreeCounter = 0;
+  if (state.recoveryWatch === undefined) state.recoveryWatch = null;
+  if (!Array.isArray(state.activity_ring)) state.activity_ring = [];
+  if (!state.task_tool_kinds || typeof state.task_tool_kinds !== "object") state.task_tool_kinds = {};
+  if (typeof state.task_tool_count !== "number") state.task_tool_count = 0;
+  if (typeof state.task_corrections !== "number") state.task_corrections = 0;
 }
 
 function main() {
@@ -155,16 +185,47 @@ function main() {
         prev_tool: last.tool || null,
         prev_file: last.file || null,
       });
+      state.correctionFreeCounter = 0;
+      state.task_corrections += 1;
+    } else {
+      state.correctionFreeCounter += 1;
+      if (state.correctionFreeCounter >= CORRECTION_FREE_THRESHOLD) {
+        appendJournal({
+          ts, session, cwd, type: "correction_free_streak",
+          streak: state.correctionFreeCounter,
+          active_skills: activeNames(state, "skill"),
+          active_agents: activeNames(state, "agent"),
+        });
+        state.correctionFreeCounter = 0;
+      }
     }
+    // Evaluate prior task (work between previous UserPromptSubmit and this one).
+    const taskKinds = Object.keys(state.task_tool_kinds);
+    if (state.task_tool_count >= TASK_TOOL_MIN &&
+        taskKinds.length >= TASK_DIVERSITY_MIN &&
+        state.task_corrections === 0) {
+      appendJournal({
+        ts, session, cwd, type: "task_completed",
+        tool_count: state.task_tool_count,
+        tool_kinds: taskKinds,
+        active_skills: activeNames(state, "skill"),
+        active_agents: activeNames(state, "agent"),
+      });
+    }
+    state.task_tool_kinds = {};
+    state.task_tool_count = 0;
+    state.task_corrections = 0;
     resetFrictionCounters(state);
   } else if (event === "PreToolUse") {
     const tool = input.tool_name;
     if (tool === "Skill") {
       const name = (input.tool_input && (input.tool_input.skill || input.tool_input.skill_name)) || "unknown";
       bumpUsage(`skill:${name}`);
+      pushActivity(state, "skill", name, ts);
     } else if (tool === "Agent") {
       const name = (input.tool_input && (input.tool_input.subagent_type || input.tool_input.agent)) || "unknown";
       bumpUsage(`agent:${name}`);
+      pushActivity(state, "agent", name, ts);
       state.session_subagents[name] = (state.session_subagents[name] || 0) + 1;
       const cumulative = readUsage(`agent:${name}`);
       const sessionCount = state.session_subagents[name];
@@ -182,6 +243,12 @@ function main() {
     const argsHash = djb2(JSON.stringify(input.tool_input || {}));
     const file = (input.tool_input && (input.tool_input.file_path || input.tool_input.path)) || null;
 
+    let struggleEmittedThisTurn = null;
+    const emit = (entry) => {
+      if (STRUGGLE_TYPES.has(entry.type)) struggleEmittedThisTurn = entry.type;
+      appendJournal(entry);
+    };
+
     const windowEntry = { tool, argsHash, file };
     if (tool === "Agent") {
       const sub = (input.tool_input && (input.tool_input.subagent_type || input.tool_input.agent)) || "unknown";
@@ -192,14 +259,14 @@ function main() {
 
     const sameToolArgs = state.tool_window.filter(e => e.tool === tool && e.argsHash === argsHash).length;
     if (sameToolArgs >= RETRY_THRESHOLD) {
-      appendJournal({ ts, session, cwd, type: "retry_loop", tool, count: sameToolArgs });
+      emit({ ts, session, cwd, type: "retry_loop", tool, count: sameToolArgs });
     }
 
     if (tool === "Agent") {
       const subagent = (input.tool_input && (input.tool_input.subagent_type || input.tool_input.agent)) || "unknown";
       const recent = state.tool_window.slice(-5).filter(e => e.tool === "Agent" && e.subagent === subagent).length;
       if (recent >= AGENT_RESPAWN_THRESHOLD) {
-        appendJournal({ ts, session, cwd, type: "weak_agent", subagent_type: subagent, count: recent });
+        emit({ ts, session, cwd, type: "weak_agent", subagent_type: subagent, count: recent });
       }
     }
 
@@ -214,14 +281,14 @@ function main() {
       if (state.last_errors.length > ERROR_RING_SIZE) state.last_errors.shift();
       const sameError = state.last_errors.filter(e => e.fp === fp).length;
       if (sameError >= ERROR_LOOP_THRESHOLD) {
-        appendJournal({ ts, session, cwd, type: "tool_error_loop", tool, count: sameError, fp });
+        emit({ ts, session, cwd, type: "tool_error_loop", tool, count: sameError, fp });
       }
     }
 
     if (file && EDIT_TOOLS.has(tool)) {
       state.edit_counts[file] = (state.edit_counts[file] || 0) + 1;
       if (state.edit_counts[file] >= EDIT_CHURN_THRESHOLD && !state.edit_churn_emitted[file]) {
-        appendJournal({ ts, session, cwd, type: "edit_churn", file, count: state.edit_counts[file] });
+        emit({ ts, session, cwd, type: "edit_churn", file, count: state.edit_counts[file] });
         state.edit_churn_emitted[file] = true;
       }
       const keys = Object.keys(state.edit_counts);
@@ -239,7 +306,7 @@ function main() {
       if (isBuildCmd && hasError) {
         state.build_failure_count += 1;
         if (state.build_failure_count >= BUILD_LOOP_THRESHOLD && !state.build_loop_emitted) {
-          appendJournal({ ts, session, cwd, type: "build_loop", count: state.build_failure_count, command: cmd.slice(0, 80) });
+          emit({ ts, session, cwd, type: "build_loop", count: state.build_failure_count, command: cmd.slice(0, 80) });
           state.build_loop_emitted = true;
         }
       }
@@ -247,9 +314,35 @@ function main() {
 
     state.tools_since_user += 1;
     if (state.tools_since_user >= DEAD_END_THRESHOLD && !state.dead_end_emitted) {
-      appendJournal({ ts, session, cwd, type: "dead_end", count: state.tools_since_user });
+      emit({ ts, session, cwd, type: "dead_end", count: state.tools_since_user });
       state.dead_end_emitted = true;
     }
+
+    state.task_tool_count += 1;
+    state.task_tool_kinds[tool] = (state.task_tool_kinds[tool] || 0) + 1;
+
+    if (struggleEmittedThisTurn) {
+      state.recoveryWatch = { recovered_from: struggleEmittedThisTurn, since_ts: ts, clean_count: 0, window_tools: [] };
+    } else if (state.recoveryWatch) {
+      const turnHadError = fp !== null;
+      if (turnHadError) {
+        state.recoveryWatch = null;
+      } else {
+        state.recoveryWatch.clean_count += 1;
+        state.recoveryWatch.window_tools.push(tool);
+        if (state.recoveryWatch.window_tools.length > CLEAN_RECOVERY_WINDOW) state.recoveryWatch.window_tools.shift();
+        if (state.recoveryWatch.clean_count >= CLEAN_RECOVERY_WINDOW) {
+          appendJournal({
+            ts, session, cwd, type: "clean_recovery",
+            recovered_from: state.recoveryWatch.recovered_from,
+            recovery_window_tools: state.recoveryWatch.window_tools.slice(),
+            active_skills: activeNames(state, "skill"),
+            active_agents: activeNames(state, "agent"),
+          });
+          state.recoveryWatch = null;
+        }
+      }
+    }
   }
 
   safeWrite(STATE, state);

install.sh

@@ -1,48 +1,216 @@
 #!/usr/bin/env bash
+# ADAM installer — pure bash + git + curl + jq.
+# Idempotent. Safe for upgrades. Supports `curl | bash` via auto-clone.
+#
+# Usage:
+#   ./install.sh                      # local install from cwd
+#   curl -fsSL <raw>/install.sh | bash
+#   VERSION=v0.3.0 ./install.sh       # pin a tag
+#   ./install.sh --yes                # skip settings.json prompt
+#   ./install.sh --dry-run            # show actions, write nothing
+
 set -euo pipefail
 
+REPO_GIT="https://github.com/lukaszraczylo/claude-adam.git"
 DEST="${HOME}/.claude"
-SRC="$(cd "$(dirname "$0")" && pwd)"
+ASSUME_YES=0
+DRY_RUN=0
+VERSION="${VERSION:-${BRANCH:-}}"   # env var pin; empty = latest tag
 
-echo "ADAM installer"
-echo "  source: $SRC"
-echo "  dest:   $DEST"
-echo
+log()  { printf '  %s\n' "$*"; }
+warn() { printf '  ! %s\n' "$*" >&2; }
+die()  { printf '  ! %s\n' "$*" >&2; exit 1; }
+run()  { if [ "$DRY_RUN" = 1 ]; then printf '    [dry-run] %s\n' "$*"; else eval "$@"; fi; }
 
-if [ ! -d "$DEST" ]; then
-  echo "  ! $DEST does not exist. Is Claude Code installed?"
-  exit 1
+# --------------------------------------------------------------------- args
+for arg in "$@"; do
+  case "$arg" in
+    --yes|-y)     ASSUME_YES=1 ;;
+    --dry-run|-n) DRY_RUN=1 ;;
+    --version=*)  VERSION="${arg#--version=}" ;;
+    --help|-h)    sed -n '2,12p' "$0"; exit 0 ;;
+    *) die "unknown arg: $arg (try --help)" ;;
+  esac
+done
+
+# --------------------------------------------------------------------- prereqs
+need() { command -v "$1" >/dev/null 2>&1 || die "missing: $1 — $2"; }
+need git  "install: brew install git || apt install git"
+need curl "install: brew install curl || apt install curl"
+need jq   "install: brew install jq || apt install jq"
+command -v node >/dev/null 2>&1 || warn "node not found — hooks need node 18+; install: brew install node"
+
+# --------------------------------------------------------------------- locate source
+# If invoked via `curl | bash`, $0 is bash and there are no local files.
+PIPED=0
+SCRIPT_PATH="${BASH_SOURCE[0]:-$0}"
+if [ ! -f "$SCRIPT_PATH" ] || [ "$SCRIPT_PATH" = "bash" ] || [ "$SCRIPT_PATH" = "-" ]; then
+  PIPED=1
+elif [ ! -d "$(dirname "$SCRIPT_PATH")/hooks" ]; then
+  PIPED=1
 fi
 
-mkdir -p \
-  "$DEST/hooks" \
-  "$DEST/agents" \
-  "$DEST/skills/adam-self-improvement" \
-  "$DEST/commands" \
-  "$DEST/adam/proposals" \
-  "$DEST/adam/applied" \
-  "$DEST/adam/rejected" \
-  "$DEST/adam/trash" \
-  "$DEST/adam/journal" \
-  "$DEST/adam/tests/fixtures"
+CLEANUP_TMP=""
+cleanup() { [ -n "$CLEANUP_TMP" ] && rm -rf "$CLEANUP_TMP" 2>/dev/null || true; }
+trap cleanup EXIT INT TERM
 
-cp "$SRC/hooks/adam-observe.mjs"                                      "$DEST/hooks/"
-cp "$SRC/hooks/adam-nudge.mjs"                                        "$DEST/hooks/"
-cp "$SRC/agents/adam.md"                                              "$DEST/agents/"
-cp "$SRC/skills/adam-self-improvement/SKILL.md"                       "$DEST/skills/adam-self-improvement/"
-cp "$SRC/commands/reflect.md"                                         "$DEST/commands/"
-cp "$SRC/adam/tests/run-tests.sh"                                     "$DEST/adam/tests/"
-cp "$SRC/adam/tests/fixtures/seed-corrections.jsonl"                  "$DEST/adam/tests/fixtures/"
+if [ "$PIPED" = 1 ]; then
+  log "running via curl|bash — cloning repo to tmp"
+  CLEANUP_TMP="$(mktemp -d -t claude-adam-install.XXXXXX)"
+  REF="$VERSION"
+  if [ -z "$REF" ]; then
+    # latest semver tag from remote (no local clone needed)
+    REF="$(git ls-remote --tags --refs "$REPO_GIT" \
+            | awk -F/ '{print $NF}' \
+            | grep -E '^v[0-9]+\.[0-9]+\.[0-9]+$' \
+            | sort -V | tail -1)"
+    [ -z "$REF" ] && REF="main"
+  fi
+  log "fetching $REF"
+  run "git clone --quiet --depth=1 --branch=\"$REF\" \"$REPO_GIT\" \"$CLEANUP_TMP\""
+  SRC="$CLEANUP_TMP"
+else
+  SRC="$(cd "$(dirname "$SCRIPT_PATH")" && pwd)"
+fi
 
-[ -f "$DEST/adam/journal.jsonl" ] || : > "$DEST/adam/journal.jsonl"
-[ -f "$DEST/adam/state.json" ]    || echo '{"cursor":0,"tool_window":[]}' > "$DEST/adam/state.json"
-[ -f "$DEST/adam/usage.json" ]    || echo '{}' > "$DEST/adam/usage.json"
+log "ADAM installer"
+log "  source: $SRC"
+log "  dest:   $DEST"
+log "  mode:   $([ "$DRY_RUN" = 1 ] && echo dry-run || echo apply)$([ "$ASSUME_YES" = 1 ] && echo ' --yes' || true)"
+log ""
 
-echo "  files installed."
-echo
-echo "  next steps:"
-echo "    1. bash $DEST/adam/tests/run-tests.sh    # must show: 18 passed, 0 failed"
-echo "    2. merge settings.json.example into $DEST/settings.json"
-echo "    3. start a fresh Claude Code session, then run /reflect"
-echo
-echo "  ADAM is dormant until you invoke /reflect."
+[ -d "$DEST" ] || die "$DEST does not exist. Install Claude Code first: https://claude.com/claude-code"
+
+# --------------------------------------------------------------------- dirs
+DIRS=(
+  "hooks" "agents" "skills/adam-self-improvement" "commands"
+  "adam/proposals" "adam/applied" "adam/rejected" "adam/trash"
+  "adam/journal" "adam/scripts" "adam/tests/fixtures"
+)
+for d in "${DIRS[@]}"; do run "mkdir -p \"$DEST/$d\""; done
+
+# .gitkeep markers so the layout survives `git init` for users who VCS ~/.claude
+for d in adam/proposals adam/applied adam/rejected adam/trash adam/journal; do
+  [ -e "$DEST/$d/.gitkeep" ] || run ": > \"$DEST/$d/.gitkeep\""
+done
+
+# --------------------------------------------------------------------- file copy
+# Conservative: if dest exists and differs from src AND user-modified after install,
+# write to <file>.adam-new and warn instead of clobbering.
+copy_file() {
+  local src="$1" dst="$2"
+  [ -f "$src" ] || die "missing source file: $src"
+  if [ -f "$dst" ] && ! cmp -s "$src" "$dst"; then
+    if [ -f "$DEST/adam/.install-marker" ] \
+       && [ "$(stat -f %m "$dst" 2>/dev/null || stat -c %Y "$dst")" \
+          -gt "$(stat -f %m "$DEST/adam/.install-marker" 2>/dev/null || stat -c %Y "$DEST/adam/.install-marker")" ]; then
+      warn "modified locally, NOT overwriting: $dst"
+      warn "  new version written to: $dst.adam-new (review and merge manually)"
+      run "cp \"$src\" \"$dst.adam-new\""
+      return
+    fi
+  fi
+  run "cp \"$src\" \"$dst\""
+  log "  copied: ${dst#$HOME/}"
+}
+
+# Hooks
+copy_file "$SRC/hooks/adam-observe.mjs"                              "$DEST/hooks/adam-observe.mjs"
+copy_file "$SRC/hooks/adam-nudge.mjs"                                "$DEST/hooks/adam-nudge.mjs"
+# Agent / skill / command
+copy_file "$SRC/agents/adam.md"                                      "$DEST/agents/adam.md"
+copy_file "$SRC/skills/adam-self-improvement/SKILL.md"               "$DEST/skills/adam-self-improvement/SKILL.md"
+copy_file "$SRC/commands/reflect.md"                                 "$DEST/commands/reflect.md"
+# Adam internals
+copy_file "$SRC/adam/scripts/adam-archive.mjs"                       "$DEST/adam/scripts/adam-archive.mjs"
+copy_file "$SRC/adam/tests/run-tests.sh"                             "$DEST/adam/tests/run-tests.sh"
+copy_file "$SRC/adam/tests/fixtures/seed-corrections.jsonl"          "$DEST/adam/tests/fixtures/seed-corrections.jsonl"
+
+# Preserve user data — never overwrite
+[ -f "$DEST/adam/journal.jsonl" ] || run ": > \"$DEST/adam/journal.jsonl\""
+[ -f "$DEST/adam/state.json" ]    || run "echo '{\"tool_window\":[]}' > \"$DEST/adam/state.json\""
+[ -f "$DEST/adam/usage.json" ]    || run "echo '{}' > \"$DEST/adam/usage.json\""
+
+# install marker — used by future runs to detect local mtime drift
+run "touch \"$DEST/adam/.install-marker\""
+
+# --------------------------------------------------------------------- settings.json
+SETTINGS="$DEST/settings.json"
+EXAMPLE="$SRC/settings.json.example"
+[ -f "$EXAMPLE" ] || die "missing $EXAMPLE"
+
+# Build target settings via jq merge (preserves all user keys/hooks).
+TMP_NEW="$(mktemp -t adam-settings.XXXXXX)"
+TMP_DIFF="$(mktemp -t adam-settings-diff.XXXXXX)"
+cleanup_full() { cleanup; rm -f "$TMP_NEW" "$TMP_DIFF" 2>/dev/null || true; }
+trap cleanup_full EXIT INT TERM
+
+if [ -f "$SETTINGS" ]; then
+  jq --slurpfile add "$EXAMPLE" '
+    . as $cur
+    | ($add[0].hooks // {}) as $new
+    | .hooks = (
+        ($cur.hooks // {}) as $cur_hooks
+        | reduce ($new | keys[]) as $k ($cur_hooks;
+            .[$k] = (
+              ((.[$k] // []) + $new[$k])
+              | unique_by(tojson)
+            )
+          )
+      )
+  ' "$SETTINGS" > "$TMP_NEW"
+else
+  jq 'del(._comment)' "$EXAMPLE" > "$TMP_NEW"
+fi
+
+if [ -f "$SETTINGS" ] && cmp -s "$SETTINGS" "$TMP_NEW"; then
+  log "settings.json already wired — no changes"
+else
+  log ""
+  log "settings.json changes proposed:"
+  if [ -f "$SETTINGS" ]; then
+    diff -u "$SETTINGS" "$TMP_NEW" > "$TMP_DIFF" || true
+  else
+    diff -u /dev/null "$TMP_NEW" > "$TMP_DIFF" || true
+  fi
+  sed 's/^/    /' "$TMP_DIFF"
+  log ""
+  if [ "$ASSUME_YES" = 1 ]; then
+    REPLY=y
+  else
+    printf '  apply settings.json changes? [y/N] '
+    read -r REPLY </dev/tty || REPLY=n
+  fi
+  case "$REPLY" in
+    y|Y|yes|YES)
+      [ -f "$SETTINGS" ] && run "cp \"$SETTINGS\" \"$SETTINGS.adam-bak.$(date +%s)\""
+      run "mv \"$TMP_NEW\" \"$SETTINGS\""
+      log "  settings.json updated (backup at *.adam-bak.<ts> if pre-existing)"
+      ;;
+    *)
+      log "  skipped — wire entries from $EXAMPLE manually"
+      ;;
+  esac
+fi
+
+# --------------------------------------------------------------------- summary
+log ""
+log "installed:"
+log "  hooks/adam-observe.mjs, hooks/adam-nudge.mjs"
+log "  agents/adam.md"
+log "  skills/adam-self-improvement/SKILL.md"
+log "  commands/reflect.md"
+log "  adam/scripts/adam-archive.mjs"
+log "  adam/tests/run-tests.sh"
+log ""
+log "preserved (if existed):"
+log "  adam/journal.jsonl, adam/state.json, adam/usage.json"
+log ""
+log "next:"
+log "  1. bash $DEST/adam/tests/run-tests.sh    # expect: all passed"
+log "  2. start a fresh Claude Code session"
+log "  3. run /reflect to invoke the analyst"
+log ""
+log "ADAM is dormant until you run /reflect."
+log "journal:   $DEST/adam/journal.jsonl"
+log "proposals: $DEST/adam/proposals/"

skills/adam-self-improvement/SKILL.md

@@ -5,8 +5,6 @@ description: Use when the user types /reflect, asks "what has adam learned", ask
 
 # adam-self-improvement
 
-You are about to drive a review session for ADAM, the self-improvement layer. You operate in the **main thread** with the user present. The `adam` subagent does the heavy analysis; you orchestrate.
-
 ## When to invoke
 
 - User types `/reflect`
@@ -44,9 +42,23 @@ For each id in `high_confidence`:
 - Verify in front of the user: print `id`, `target`, `confidence`, `blast_radius`, `cross_session_evidence`, `auto_apply_eligible`.
 - Apply the change:
   - **For `skill_new`**: `mkdir -p ~/.claude/skills/<slug>/`, then `Write` the proposal's `# Proposed change` body to `~/.claude/skills/<slug>/SKILL.md`. After write, print: "skill `<slug>` written to `~/.claude/skills/<slug>/SKILL.md` — activates immediately — Claude Code v2.1.0+ auto-hot-reloads user-level skills, no restart needed."
-  - **For `memory`**: `Write` the proposal's `# Proposed change` body to the path in `target` (under `~/.claude/projects/<encoded-home>/memory/`, where `<encoded-home>` is the user's home dir with `/` replaced by `-`, e.g. `-Users-alice` on macOS). Then update `MEMORY.md` index with a one-line pointer.
-  - **For other types under auto-apply**: apply via Write/Edit per `# Proposed change`. (Note: only `memory` and `skill_new` qualify for auto-apply per the rubric.)
+  - **For `memory`**: `Write` the proposal's `# Proposed change` body (which MUST include the auto-memory frontmatter — see "Memory drafting protocol" in `agents/adam.md`) to the path in `target`. Then update `MEMORY.md` index with a one-line pointer.
+  - **For `skill_edit`**: enforce the apply-time gate before writing.
+    1. Verify proposal frontmatter has `auto_apply_eligible: true`. If not, abort and queue for review.
+    2. Read `target` SKILL.md, capture `current_bytes` from a fresh stat — do NOT trust frontmatter `bytes_before`.
+    3. Verify diff in `# Proposed change`:
+       - Unified-diff format.
+       - Zero `-` lines on existing SKILL.md content (additions only).
+       - Total `+` lines ≤ 30.
+       If any check fails, print one-line refusal reason, leave proposal in `proposals/`, continue.
+    4. Cooldown re-check: scan `applied/` frontmatter for `target` matching this and `last_auto_edit` newer than 7 days ago. Refuse if found.
+    5. Blacklist re-check: scan `rejected/` frontmatter for `target` matching this and `auto_apply_blacklist: true` newer than 30 days ago. Refuse if found.
+    6. Apply via `Edit` tool (append the new section per the diff). Never use `Write` on existing SKILL.md.
+    7. Re-stat target. If new size exceeds `2 * current_bytes` (captured in step 2), revert via `Edit` (remove the just-appended section) and refuse — print refusal reason.
+    8. Add `last_auto_edit: <iso8601 utc now>` to the proposal frontmatter before moving it.
+    9. Tell user: "skill `<slug>` extended (added <N> lines) — auto-applied via win-evidence gate."
 - Move proposal to `~/.claude/adam/applied/<UTC-ts>-<id>.md`.
+- **Archive consumed journal entries**: `node ~/.claude/adam/scripts/adam-archive.mjs ~/.claude/adam/applied/<UTC-ts>-<id>.md` — moves entries listed in proposal's `source_entries` from `journal.jsonl` to `journal/actioned-<id>.jsonl` so subsequent `/reflect` runs do not re-cluster them.
 
 Print: `auto-applied N proposals: [ids]`.
 
@@ -61,10 +73,11 @@ c. On **approve**:
    - For `deletion`: `mkdir -p ~/.claude/adam/trash/<ts>` then `mv` the artifact into it. Print restoration command.
    - For `skill_new`: `mkdir -p ~/.claude/skills/<slug>/`, then write `# Proposed change` body to `<slug>/SKILL.md`. Tell user: "skill `<slug>` written — activates immediately (CC v2.1.0+ auto-hot-reload)."
    - For `skill_edit`: apply the unified diff in `# Proposed change` to the existing SKILL.md at `target` (append-only — never replace existing content).
-   - For `memory`: write to `target` and update `MEMORY.md` index.
+   - For `memory`: write `# Proposed change` body (must include auto-memory frontmatter) to `target` and update `MEMORY.md` index with a one-line pointer.
    - For all others: apply via Write/Edit per the proposal's `# Proposed change`.
    - Move proposal to `~/.claude/adam/applied/<ts>-<id>.md`.
-d. On **reject**: ask for reason in one line. Append `# Reason\n<reason>` to proposal body. Move to `~/.claude/adam/rejected/<id>.md`.
+   - Archive: `node ~/.claude/adam/scripts/adam-archive.mjs ~/.claude/adam/applied/<ts>-<id>.md`.
+d. On **reject**: ask for reason in one line. Append `# Reason\n<reason>` to proposal body. If the proposal `type` is `skill_edit`, ALSO add `auto_apply_blacklist: true` to its frontmatter (so future reflects skip auto-apply on this target for 30 days). Move to `~/.claude/adam/rejected/<id>.md`. Archive: `node ~/.claude/adam/scripts/adam-archive.mjs ~/.claude/adam/rejected/<id>.md`.
 e. On **edit**: ask the user for the change, edit the proposal in place, then loop back to step 3a for that same id.
 
 ### 4. Handle failures
@@ -89,12 +102,16 @@ adam reflect summary:
 
 Before writing any proposal:
 - Confirm `# Assumptions` section is non-empty.
+- Confirm `# Diagnosis` section exists and contains all four labelled lines (`Trigger:`, `Action:`, `Mismatch:`, `Outcome:`) AND at least one backtick-wrapped quote ≤80 chars in the Outcome line. Refuse if missing or malformed — agent must redraft per the "Diagnosis drafting protocol" in `agents/adam.md`.
 - Confirm `# Success criterion` section is non-empty and runnable.
 - Confirm change is ≤50 LOC for non-`skill_new`, or ≤80 LOC for `skill_new` body. If larger, ask the user once: "this proposal is N LOC — proceed?"
 - For `claude_md_edit`: confirm 3+ distinct cwds in the `# Why` section.
 - For `deletion`: confirm both criteria (a) and (b) from the agent's special handling are documented in the proposal.
 - For `skill_new`: confirm the slug doesn't collide with any existing skill in `~/.claude/skills/`. If it does, refuse and ask user to rename.
-- For `skill_edit`: confirm the diff is append-only (no `-` lines that remove existing content) and that target SKILL.md exists.
+- For `skill_edit`: confirm the diff is append-only (no `-` lines that remove existing content) and that target SKILL.md exists. When auto-applying, ALSO re-verify the eligibility gate steps in §2 (cooldown, blacklist, byte cap) before any `Edit` call — never trust frontmatter alone.
+- For `skill_edit` with `auto_apply_eligible: true`: confirm `contradiction_flag` is absent or null in frontmatter. Refuse auto-apply if `contradiction_flag` is set with any non-empty value (treat the agent's flag as a hard veto on auto-apply; user can still manually approve in walk-the-queue if they disagree with the heuristic).
+- For `memory`: confirm `# Proposed change` body starts with `---` frontmatter containing required fields `name`, `description`, `type`, `originSessionId`. Refuse if frontmatter missing — agent must redraft per the Memory drafting protocol.
+- Confirm `source_entries` is present in proposal frontmatter as a non-empty list (used for archive). Warn (do not refuse) if missing — legacy proposals from before v0.2.0 won't have it.
 
 If any check fails, refuse to apply and ask the user how to proceed.