Replaces the geometric-A-with-observation-dot with a softer, more
on-theme design: a swaddled-baby silhouette (rounded A-shape bundle),
face nestled inside, and the wrap-band extended past the bundle on
both sides as little hands. Maintains currentColor + zero external
assets; reads cleanly down to favicon size.
Ties the visual identity to the 'Story behind Adam' section: the
project is named after the author's son, and now the logo is too.
- New 'Story behind Adam' section at the top: the project is named after
the author's newborn son, whose observe-act-adjust-observe-again
learning loop is the methodology ADAM applies to LLM sessions.
- New SVG logo at assets/logo.svg: stylized 'A' with a captured
observation point inside the apex and a feedback crossbar. Uses
currentColor + gradient so it adapts to light/dark GitHub themes.
- Centered header block with project tagline + 5 badges (License,
Version, Tests, Node, Platform).
- New 'Highlights' section: 8 emoji-tagged one-liners covering the
v0.3.3 design pillars (zero LLM cost observation, A/B measurement,
sliding windows, observability, etc.).
- New 'How it works' ASCII pipeline diagram: observation -> analysis
pre-processors -> analyst -> review + apply.
- Signals table now includes per-signal sliding window column.
- Rubric section restructured: gates, modifiers (dampener), and
skill_edit-specific requirements clearly separated.
- New 'Inspecting the analyst's reasoning' section documenting
adam-explain.mjs + /reflect --explain.
- Layout updated for v0.3.3 state files (active-nudges.json,
ab-tracking.jsonl, reinforcements.jsonl, last-trace.txt) and all
9 new helper scripts under adam/scripts/.
- Test count: 27 -> 87.
- Closing line crediting Adam.
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).
Closes the gap between categorical signal capture (we saw 3 retries) and
causal proposal drafting (here is why and what to do). Mirrors the NL trace
reflection step Hermes Agent uses before mutating prompts.
Adds # Diagnosis section to every proposal body — four labelled lines:
- Trigger: what the user wanted / context
- Action: what the assistant did
- Mismatch: how the action diverged
- Outcome: surfacing event with >=1 verbatim transcript quote
Constraints:
- <=5 LOC of prose total
- >=1 backtick-wrapped quote <=80 chars from transcript context window
- Cannot speculate; "Mismatch: unclear" is allowed but takes -1 confidence
- Win clusters use "Mismatch: None" with recovery quote in Outcome
Skill enforces structure at apply time (presence + 4 labelled lines + quote)
for both auto-apply and walk-the-queue paths. No semantic check — humans
judge causal correctness during walk-the-queue.
Adds optional frontmatter field `diagnosis_summary` (<=120 chars from the
Mismatch line) so applied/ and rejected/ are searchable by causal pattern.
New rubric penalty: -1 confidence when Diagnosis flags Mismatch: unclear.
Stops weak-causation proposals from auto-applying (drops below conf>=4).
No hook changes. All 27 tests still pass.
Spec: ~/.claude/docs/superpowers/specs/2026-05-10-adam-causal-diagnosis-design.md
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
Lifecycle redesign:
- Each proposal records source_entries: [<ts>...] in frontmatter listing
the journal timestamps that fed its cluster.
- After apply/reject, skill calls adam/scripts/adam-archive.mjs which moves
matching entries from journal.jsonl to journal/actioned-<id>.jsonl.
- Agent reads applied/ + rejected/ frontmatter on each /reflect, builds an
excluded-timestamps set, skips any leftover already-actioned entries.
- cursor field in state.json is vestigial; agent ignores it.
Effect: journal stays bounded by active observations. Rule changes
re-evaluate the remainder without manual rewind. Race-safer for parallel
sessions on shared state.json (no cursor write contention).
Memory drafting:
- agents/adam.md adds 'Memory drafting protocol' parallel to Skill drafting.
- Memory proposals MUST contain auto-memory frontmatter (name, description,
type, originSessionId) in '# Proposed change' body.
- Skill enforces frontmatter check at apply time; refuses if missing.
Tests: 18 -> 21. Two new tests for adam-archive happy path + no-op.
Migration: existing applied proposals lack source_entries. Their backing
journal entries archived as a one-time bulk migration; legacy proposals
annotated with migration note.
The hook emits struggle signals only after crossing internal thresholds
(3 retries, 8 tools no-prompt, 4 edits to one file, 2 build failures, etc.).
Each journal entry is therefore meaningful evidence on its own. Old rule
required >=3 entries within single session, which the once-per-thing
emission design rarely produces. New rule: >=1 struggle entry qualifies
for proposal at +2 weight (cross-session bonus does not stack).
Auto-apply still requires cross_session_evidence; single-session-only
proposals always queue for review.
- 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