/evolve

name: evolve
user-invocable: false
tags: [learning, intelligence, meta]
model: sonnet
model-preference: sonnet
model-preference-codex: gpt-5.4-mini
model-preference-cursor: claude-sonnet-4-6
args-schema:
  - flag: --apply
    description: "Apply dialectic-derived diff to USER.md + AGENT.md"
  - flag: --dry-run
    description: "Show diff without writing (default)"
  - flag: --model <name>
    description: "Override single-pass LLM (haiku|sonnet|opus)"
  - flag: --budget-tokens <N>
    description: "Token budget for derivation prompt (default 8000)"
description: >
  Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session history),
  review (edit/manage existing learnings), list (display active learnings). Manages .orchestrator/metrics/learnings.jsonl.

> **Platform Note:** State files use the platform's native directory: `.claude/` (Claude Code), `.codex/` (Codex CLI), or `.cursor/` (Cursor IDE). Shared metrics live in `.orchestrator/metrics/` (v2) with fallback to `<state-dir>/metrics/` for pre-v2.0 legacy data. See `skills/_shared/platform-tools.md`.

Evolve Skill

Phase 0: Bootstrap Gate

Read `skills/_shared/bootstrap-gate.md` and execute the gate check. If the gate is CLOSED, invoke `skills/bootstrap/SKILL.md` and wait for completion before proceeding. If the gate is OPEN, continue to Phase 1.

<HARD-GATE> Do NOT proceed past Phase 0 if GATE_CLOSED. There is no bypass. Refer to `skills/_shared/bootstrap-gate.md` for the full HARD-GATE constraints. </HARD-GATE>

Phase 1: Config & Data Loading

**Telemetry start marker (#1200):** note the current wall-clock time before Step 1.1 runs (e.g. `date +%s%3N`, or the coordinator's own turn-start instant). Every `orchestrator.evolve.completed` emit in Phase 1 / Phase 3 below reports `duration_ms` (placeholder `DURATION_MS`) as the elapsed milliseconds since this marker — same in-memory-value convention as `CT`/`AC`/`ASK`/`DROP` in `skills/session-end/SKILL.md`'s `orchestrator.handover.gated` emits.

1.1 Read Session Config

Read and parse Session Config per `skills/_shared/config-reading.md`. Store result as `$CONFIG`.

1.2 Check Persistence

Extract `persistence` from `$CONFIG`. If `persistence` is `false`, abort with message:

> "Learnings require persistence to be enabled in Session Config. Add `persistence: true` to your Session Config block (CLAUDE.md for Claude Code, AGENTS.md for Codex CLI)."

**Telemetry on abort (#1200, #1206):** before stopping, emit the abort form of the run-completion event. Kept as a minimal `emit-event.mjs` call, not routed through `scripts/sweep-expired-learnings.mjs` — no store-write CLI has run yet at this gate (it fires before Step 1.4 even reads `learnings.jsonl`), so there is no mechanical pipeline call site to fold this emit into, unlike the Step 3.5(5)/(6) success path below:

node scripts/emit-event.mjs --type orchestrator.evolve.completed --payload \
  "$(node -e "process.stdout.write(JSON.stringify({aborted: 'persistence-disabled', reason: 'Learnings require persistence to be enabled in Session Config.'.slice(0,300), duration_ms: DURATION_MS}))")"

1.3 Determine Mode

Read mode from `$ARGUMENTS`:

• If empty or not provided, default to `analyze`
• Valid modes: `analyze`, `review`, `list`, `dialectic`
• If invalid mode provided, report error and list valid modes

1.4 Load Data

**Lazy-create defensive (#185):** If `.orchestrator/metrics/learnings.jsonl` does not exist (pre-#185 repo or bootstrap skipped), create an empty file and emit an info log — do NOT hard-fail:

LEARNINGS_FILE=".orchestrator/metrics/learnings.jsonl"
if [[ ! -f "$LEARNINGS_FILE" ]]; then
  mkdir -p "$(dirname "$LEARNINGS_FILE")"
  : > "$LEARNINGS_FILE"
  echo "info(#185): auto-created $LEARNINGS_FILE (was missing)" >&2
fi

This defensive step is idempotent and cheap — it ensures `/evolve analyze|review|list` never fails because of a missing artifact file.

1. Read `.orchestrator/metrics/sessions.jsonl` (session history). If it does not exist, check `<state-dir>/metrics/sessions.jsonl` as a legacy fallback (where `<state-dir>` is `.claude/`, `.codex/`, or `.cursor/` per platform). If neither exists, warn: "No session history found. Run at least one session first." 2. Read `.orchestrator/metrics/learnings.jsonl` if it exists. If not found, check `<state-dir>/metrics/learnings.jsonl` as a legacy fallback. 3. Count existing learnings, note any where `expires_at` < current date (expired)

Phase 2: Mode Dispatch

Route based on mode:

• `analyze` → Phase 3
• `review` → Phase 4
• `list` → Phase 5
• `dialectic` → Phase 6

---

Phase 3: Analyze Mode (default)

Extracts learnings from session history: pattern extraction across the 9 built-in analyzer types plus `evolve.extra-sources`, deduplication, relation judgment (#1016), the AskUserQuestion confirmation gate, and the archive-safe write pipeline (through the C2 auto-repair feeder). See [references/evolve-analyze-mode.md](references/evolve-analyze-mode.md). **Read WHEN:** Phase 2's Mode Dispatch routes to `analyze` (the default mode).

---

Phase 4: Review Mode

Interactive management of existing learnings.

Step 4.1: Load Learnings

• Read `.orchestrator/metrics/learnings.jsonl`. If not found, check `<state-dir>/metrics/learnings.jsonl` as a legacy fallback.
• If neither exists or both are empty: "No learnings found. Run `/evolve analyze` first."
• Parse each line as JSON

Step 4.2: Display Learnings

Present a formatted table grouped by type. Include the **Effective** column — the recency-decayed surfacing score (#670) — so stale high-confidence entries are visible as decay candidates next to their static confidence:

## Active Learnings

| # | Type | Subject | Confidence | Effective | Expires | Insight |
|---|------|---------|------------|-----------|---------|---------|
| 1 | fragile-file | src/lib/auth.ts | 0.80 | 0.78 | 2026-07-05 | Changed in 4 of la