Adds a lightweight "new release available" notice without auto-installing —
because re-running install.sh overwrites ADAM's own /reflect-applied skill
edits, so the user must choose when to take an update.
- install.sh writes ~/.claude/adam/.version (the installed release tag) on
every install. Derived from $VERSION / piped REF / `git describe --tags`.
- adam-nudge.mjs (SessionStart) compares .version against the latest GitHub
release at most once/day. Cached in ~/.claude/adam/.update-check.json; the
cache drives an instant nudge (no network on the hot path) and is refreshed
best-effort with a 1.5s AbortController cap. fetch unavailable / offline /
timeout / rate-limit / parse error all degrade to silent no-op. Opt out with
ADAM_NO_UPDATE_CHECK=1. main() is now async; never blocks SessionStart.
- README: "Staying up to date" section; pin example bumped to v0.6.3.
Tests: 134 -> 138. Notifier verified fully offline (cache-driven): nudges when
a newer release is cached, silent when current, suppressed by the opt-out env,
and no-ops when the .version marker is absent.
Proposed and approved through ADAM's own /reflect harness_edit loop (MOSS §1):
the analyst surfaced 23 tool_error_loop entries across 4 sessions whose context
windows were really redundant re-reads of one file.
retry_loop keys on argsHash of the full tool_input (including offset/limit), so
consecutive Reads of the SAME file at different offsets escaped dedup and leaked
into tool_error_loop fingerprints. The new file_reread signal catches them:
same file Read >=3x in the 10-event window, offset-agnostic (keyed on file
path), guarded by `sameToolArgs < RETRY_THRESHOLD` so byte-identical reads stay
with retry_loop (no double-count).
Fully wired end-to-end (not a half-dead signal):
- adam-observe.mjs: detection + STRUGGLE_TYPES membership (so it carries
context_window + active_skills like other struggle signals).
- adam-window.mjs: 14-day sliding window (task-local, like retry_loop).
- adam-score.mjs: severity divisor 3.
- adam-batch.mjs: file-basename clustering.
- agents/adam.md + README: signal tables, clustering rules, rubric, windows.
Tests: 126 -> 132 (file_reread fires on 3x offset-shifted reads, not on 2x;
byte-identical reads route to retry_loop not file_reread; carries context_window).
Full codebase review (multi-agent, adversarially verified) surfaced several
documented-but-dead mechanisms and doc/code drift. Fixes:
- adam-observe: struggle signals now emit `active_skills`, so silent_drift's
primary cluster key AND §5b skill-attribution sub-clustering (+1 rubric
bonus) actually fire — both were silently dead (no struggle signal carried
the field).
- adam-cooldown: new `--compute` CLI deterministically derives
proposal_fingerprint. The exported computeProposalFingerprint() was never
called and the analyst was told to hand-compute a djb2 hash it cannot
reproduce. Spec now mandates a *stable* cluster id so fingerprints reproduce
across /reflect runs. Removed one dead normalization line.
- spec: reinforcement proposals excluded from A/B tracking — agents/adam.md
contradicted itself (:376 included, :476 excluded); SKILL.md aligned.
- adam-nudge: PENDING_CHECK_PATHS now mirrors the full install set
(adam-utils / adam-batch / adam-rollback were missing).
- adam-explain: synthesized clustering summary carries `regressions: 0`
(structural consistency with parsed summaries).
- docs: test-count drift (87/94 -> 126) and "350-line hook" (-> ~600) fixed;
adam-score header documents severity_sum/severity_by_type; adam-batch §4
reference corrected.
Tests: +12 assertions (114 -> 126), all green. New regression tests cover the
active_skills fix and --compute, plus boundary gaps the review flagged:
retry_loop/weak_agent thresholds, A/B exact +/-25% deltas, cooldown 30d
blacklist edge.
- New signal types in hooks/adam-observe.mjs:
- silent_drift: 5 consecutive read-only PostToolUse without an action tool
- error_after_recovery: same error fingerprint returns within 5 events of clean_recovery
- Severity-weighted scoring in adam/scripts/adam-score.mjs:
- SEVERITY_DIVISORS exported per struggle signal type
- Per-session severity_sum + severity_by_type added to JSON output
- Skill-attribution clustering in agents/adam.md:
- Sub-cluster struggle signals on active_skills[0]
- New struggle-driven skill_edit variant (always queues, never auto-applies)
- Rubric updates:
- +1 for cluster severity-sum >= 10, additional +1 for >= 32
- +1 for skill-attributed sub-cluster naming an existing skill
- silent_drift + error_after_recovery added to struggle signal list
- Window: silent_drift 14d, error_after_recovery 30d
- Tests: 94 passing (78-82 new)
Backward compat: entries without count default to severity 1. Existing
win-driven skill_edit gate untouched. No journal migration.
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
Bug fixes (HIGH):
- adam-observe.mjs: errorFingerprint no longer false-positives when
toolResponse.is_error === false; ERROR_RE only used as fallback when
is_error is undefined.
- adam-observe.mjs: resetSessionLocal now clears tool_window so retry_loop
cannot fire on the first tool of a new session by matching prior session.
- adam-archive.mjs: ts dedup uses Map<ts, count> instead of Set<ts>; two
journal entries sharing a millisecond are no longer both archived when
only one is referenced in source_entries.
- adam-nudge.mjs: only counts proposal filenames matching
/^\d{4}-\d{2}-\d{3}-/ pattern; README/notes in proposals/ no longer bump.
- skills/adam-self-improvement/SKILL.md: contradiction_flag veto now applied
at apply time (carry-over from earlier review).
Test isolation:
- adam/tests/run-tests.sh: ALWAYS runs against an isolated $HOME under
mktemp -d. Previously truncated live ~/.claude/adam/journal.jsonl on
every run — destructive on production state.
Conciseness:
- agents/adam.md: -19 LOC (cuts: vestigial cursor sentence, duplicate
not-do bullets, blast-radius bullet collapse, Inputs paths delegate to
SKILL.md, win-cluster-vs-struggle-cluster commentary already enforced
by cluster-key separation, # Overlap section spec compressed).
- skills/adam-self-improvement/SKILL.md: -4 LOC (framing paragraph, dead
catch-all bullet for non-eligible types).
Auto-prune script DELETED:
- The cumulative-count primitive cannot distinguish "never used" from
"used before tracking began"; mtime gate is meaningless for installed
files. Auto-prune deferred to v0.4 with a per-key lastSeen schema.
Cross-platform:
- macOS (BSD coreutils) and Linux (Alpine, glibc + musl) verified.
- All scripts use portable forms (stat -f || stat -c, mktemp -d -t).
- README documents platform support explicitly.
DX overhaul:
- install.sh: hardened — supports `curl | bash` via auto-clone,
--version=vX.Y.Z pinning, --yes / --dry-run flags, jq-based
settings.json merge with diff prompt and backup, conservative file
copy that detects local mtime drift and writes <file>.adam-new
instead of clobbering, idempotent across re-runs.
- adam-uninstall.sh: NEW. Soft-archives ~/.claude/adam/ to .bak.<ts>/
by default; --purge to delete; --yes for non-interactive; jq-based
settings.json cleanup with diff prompt.
- README.md: curl one-liner install + version-pinned variant at top,
What's New section through v0.3.1, upgrade-safe data files callout,
uninstaller documentation, platform support note, expanded rubric
showing skill_edit gate.
Test count: 27 passed, 0 failed (was 27 — no regression).
Adds two new hook signal types:
- correction_free_streak: 5 consecutive UserPromptSubmits without a correction phrase
- clean_recovery: 3 clean PostToolUse events after a struggle signal
(tool_error_loop / dead_end / retry_loop)
Both carry active_skills/active_agents payloads computed from a 10-event
activity ring, so ADAM can attribute wins to whichever skill was active
during the streak/recovery.
Promotes skill_edit to auto-apply under a strict gate (all required):
- conf >= 4 + cross-session evidence (existing rules)
- # Why cites a win-signal entry whose active_skills includes target
- diff append-only, +lines <= 30
- resulting SKILL.md size <= 2x current size
- 7-day cooldown per target (last_auto_edit in applied/ frontmatter)
- 30-day blacklist on user rejection (auto_apply_blacklist in rejected/)
Skill enforces the gate at apply time as defense in depth: re-stats target,
re-checks cooldown and blacklist, verifies append-only, reverts and refuses
on byte-cap breach. User-rejected skill_edit proposals automatically write
auto_apply_blacklist: true.
Win signals participate in the existing v0.2.0 source_entries archive
lifecycle, so already-applied evidence does not re-cluster.
Test suite: +5 cases (5 new asserts pass), 27 total passing.
Spec: ~/.claude/docs/superpowers/specs/2026-05-10-adam-proactive-design.md
Plan: ~/.claude/docs/superpowers/plans/2026-05-10-adam-proactive.md
- 8 friction signals via lightweight hook (correction, retry_loop, weak_agent,
tool_error_loop, dead_end, edit_churn, build_loop, subagent_dispatch_pattern)
- Deterministic confidence rubric with cross-session evidence gate
- /reflect skill to dispatch the analyst subagent and walk the queue
- Skill overlap detection (prefer skill_edit over skill_new on collision)
- Solution synthesis from transcript context for new skill drafts
- Soft-delete trash, never hard rm
- 18 tests covering all signals
lukaszraczylo