feat(skills): /brain-retro — observer evidence aggregator

Read-only skill at .claude/skills/brain-retro/. Aggregates JSONL
evidence + optional notes for owner review. Side-effect: bumps
docs/observer/.read-counter.json (used by C3 observer-of-observer
54-week self-prune).

Includes Factor analysis matrix (v1.1+ amendment): 5 axes
(triggers_matched / candidates_dropped_because / boundaries_applied /
hard_floor.rules / task_classification) + cross-tab factor×factor.

Never auto-edits normative files. Per Pravila §16.2 + ADR-011 +
spec v1.1 §5.5.

+cspell словарь «разруливают», «брейн».

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

.claude/skills/brain-retro/SKILL.md

@@ -0,0 +1,40 @@
+---
+name: brain-retro
+description: Use ONCE PER SPRINT (or by explicit user invocation "брейн-ретро") to aggregate evidence from docs/observer/episodes-*.jsonl + notes/*.md and propose regulatory candidates. Read-only — never edits Tooling/Pravila/PSR_v1 automatically; only proposes.
+---
+
+# Brain Retro
+
+Aggregator over observer evidence. Reads JSONL + optional MD notes, surfaces candidates for normative updates. User decides what to apply.
+
+## When to invoke
+
+- Explicit user request: «брейн-ретро» / «сделай brain-retro» / `/brain-retro`.
+- Periodic — owner discretion (e.g. end of sprint).
+- NOT auto-invoked.
+
+## What it does NOT do
+
+- Does NOT edit `docs/Tooling_v8_3.md`, `docs/Pravila_raboty_Claude_v1_1.md`, `docs/Plugin_stack_rules_v1.md`, `CLAUDE.md`, or any normative file.
+- Does NOT write to `docs/observer/episodes-*.jsonl` (read-only).
+- Does NOT trigger automatic memory updates.
+
+## Procedure
+
+1. **Determine period**: ask user «за какой период» or default to «since last brain-retro» (find latest `docs/observer/notes/YYYY-MM-DD-brain-retro-*.md`).
+2. **Read evidence**: glob `docs/observer/episodes-YYYY-MM.jsonl` for the period; read all lines as JSON.
+3. **Read optional notes**: glob `docs/observer/notes/*.md` filtered by date.
+4. **Update read-counter**: bump `docs/observer/.read-counter.json` `last_read_at` to now, increment `read_count_last_period`. (Side-effect — used by C3 observer-of-observer.)
+5. **Aggregate** per `references/aggregation-template.md` — includes Factor analysis matrix (v1.1+) on 5 axes.
+6. **Propose candidates** — clearly separated section «Candidates for owner review». Each candidate has rationale + suggested edit + rejection-option.
+7. **Save retro note**: `docs/observer/notes/YYYY-MM-DD-brain-retro.md` with full aggregation.
+8. **Report to user**: high-signal summary.
+
+## Output anatomy
+
+See `references/aggregation-template.md`.
+
+## Behavioral rule reminders
+
+- **«Не использован ≠ проблема»** — when reporting node usage counts, NEVER mark unused nodes as «zombie» / «removal candidate». Cite `memory/feedback_brain_unused_tools_not_problem.md`.
+- **No auto-edit** — every regulatory suggestion is a candidate, not an action.

.claude/skills/brain-retro/references/aggregation-template.md

@@ -0,0 +1,115 @@
+# Brain-retro aggregation template
+
+## Period
+
+YYYY-MM-DD .. YYYY-MM-DD ({N} sessions)
+
+## Path-type distribution
+
+| path_type | count | % |
+|---|---|---|
+| regulated | A | x% |
+| improvised | B | y% |
+| alternative | C | z% |
+| mixed | D | w% |
+
+## Outcome distribution
+
+| outcome | count |
+|---|---|
+| success | M |
+| partial | N |
+| failure | O |
+| aborted | P |
+
+## Top nodes used (from `skill_invoked` events)
+
+| node | times used | first / last |
+|---|---|---|
+
+## Factor analysis matrix (v1.1+ — from `routing_decision` events + `primary_rationale`)
+
+Per-node breakdown by 5 factor axes (per spec §5.2.1).
+
+### Axis 1: triggers_matched → node
+
+«Какие триггеры чаще всего ведут к этому узлу»
+
+| node | trigger | count |
+|---|---|---|
+
+### Axis 2: candidates_considered.dropped_because → node
+
+«Какие альтернативы и почему отбрасываются в пользу этого узла»
+
+| node | dropped alternative | dropped_because (top reason) | count |
+|---|---|---|---|
+
+### Axis 3: boundaries_applied → node
+
+«Какие ADR / R-rules чаще всего разруливают в пользу этого узла»
+
+| node | boundary (ADR-NNN / PSR R-rule) | count |
+|---|---|---|
+
+### Axis 4: hard_floor.rules → invoked frequency
+
+«Как часто узел вынуждается hard-floor §12/§14/§15»
+
+| node | rule | invoked-count | total decisions | % forced |
+|---|---|---|---|---|
+
+### Axis 5: task_classification → node
+
+«В каких классах задач узел доминирует»
+
+| task_classification | top node | secondary nodes |
+|---|---|---|
+
+### Cross-tab: factor × factor
+
+Pairs of factors that co-occur to resolve specific conflicts (e.g. «ADR-009 ↔ triggers_matched=['discovery']» — 8 раз).
+
+| factor pair | combined count | interpretation |
+|---|---|---|
+
+## Canonical chains L1–L12 hit rate
+
+| chain | times | notes |
+|---|---|---|
+
+## Improvised chains (path_type=improvised, repeated ≥2)
+
+| node-set | times | candidate L13+? |
+|---|---|---|
+
+## chain_divergence cases
+
+| canonical | chosen | reason | recurring? |
+|---|---|---|---|
+
+## Top error classes
+
+| error class | count | recovery pattern |
+|---|---|---|
+
+## confusion_marker hot-spots
+
+| context | count |
+|---|---|
+
+## Candidates for owner review
+
+### Candidate 1: `<title>`
+
+- **Type**: new canonical chain L13+ / new ADR / boundary clarification / etc.
+- **Evidence**: refs to JSONL lines (file:line).
+- **Suggested action**: `<concrete edit>`.
+- **Cost / risk**: `<brief>`.
+
+(repeat for each candidate; could be 0)
+
+## Informational metrics (NOT alerts)
+
+- Nodes used at least once this period: K / 60+
+- Nodes never used since beginning of observer logs: L / 60+ — **not a problem** per [feedback_brain_unused_tools_not_problem](../../../memory/feedback_brain_unused_tools_not_problem.md)

cspell-words.txt

@@ -1463,4 +1463,6 @@ CCS
 версионный
 стейлнес
 апдейты
+разруливают
+брейн
 нодов