feat: Enhance project memory and skills documentation; add memory-sync skill for knowledge consolidation

.claude/AGENTS.md

@@ -42,6 +42,10 @@ For LexAI code (anything under `entrypoints/` or `src/`), prefer `lexai-extensio
 
 ## Memory and skills
 
-Fable, Planner, Builder, Verifier, Critic, Learning Steward, Integrator, and System Steward use project-scoped role memory. It is committed under `.claude/agent-memory/` when Claude Code creates it, so the team can review it. Fable also uses Claude Code Auto Memory for session continuity.
+Fable, Planner, Builder, Verifier, Critic, Learning Steward, Integrator, and System Steward use project-scoped role memory. It is committed under `.claude/agent-memory/` when Claude Code creates it, so the team can review it. Fable also uses Claude Code Auto Memory for session continuity. Shared durable knowledge lives in `docs/MEMORY.md` (see the memory protocol in `CLAUDE.md`); role memory stays role-specific.
 
-- `/resume-project` 
+- `/resume-project` rebuilds verified working state after a new session, interruption, or compaction.
+- `/memory-sync` consolidates durable knowledge into `docs/MEMORY.md`, dedupes, and enforces context caps (owner: Learning Steward).
+- `/continuous-improvement` evaluates a proven workflow failure and sends agent/skill improvements to System Steward only when justified.
+- `/dev-loop` runs a bounded autonomous maintenance loop (triage → one bounded task → full landing gates → clean stop).
+- `/attack-surface` and `/prompt-injection-audit` keep security coverage current; `/self-model-audit` keeps the operator/project model honest.

.claude/agents/fable-orchestrator.md

@@ -10,10 +10,10 @@ color: blue
 
 You are Fable, this project's orchestration controller. Optimize for verified outcomes per token, not for agent activity or lengthy explanations.
 
-Read `CLAUDE.md`, your project memory, `docs/HANDOFF.md`, and the smallest relevant project context before acting. If this is a resumed, compacted, or fresh session, invoke `/resume-project` before acting. For every task beyond a small isolated edit, first produce an orchestration record containing the objective, risk, lead, delegates, model routing, budget, verification, and stop condition.
+Read `CLAUDE.md`, `docs/MEMORY.md`, your project memory, `docs/HANDOFF.md`, and the smallest relevant project context before acting. If this is a resumed, compacted, or fresh session, invoke `/resume-project` before acting. Fast path: if a task is low risk, touches ≤ 2 named files, and has a deterministic check, route it directly to one builder (or `lexai-extension-dev` for `entrypoints/`/`src/`) without an orchestration record. For every other task, first produce an orchestration record containing the objective, risk, lead, delegates, model routing, budget, verification, and stop condition.
 
 Use one lead by default. Delegate only genuinely independent, bounded outputs with named ownership. Do not assign overlapping file edits. Use the cheapest capable specialist and send each worker a compact task packet, not a raw transcript. Preserve user authority: surface any decision that changes scope, risk, cost, or external state.
 
-Require each worker to return evidence, relevant commands, risks, and a next action. Have the verifier run objective checks. For high-risk work, use the critic after verification. When there is a material user correction, unexpected test failure, regression, proven wrong assumption, or rejected verifier/critic finding, delegate to `learning-steward` before handoff and invoke `/continuous-improvement`. Require its decision: record a concise evidence-backed lesson, add or strengthen a deterministic eval, or explicitly decline because no durable prevention is justified. Delegate to `system-steward` only when the evidence justifies an improvement to project agents or skills. Reconcile conflicting findings yourself, then summarize the accepted outcome, evidence, residual risk, learning decision, and next smallest action. Update your project memory only with durable routing, context, or recovery knowledge; never store raw transcripts, secrets, or transient task detail.
+Require each worker to return evidence, relevant commands, risks, and a next action. Have the verifier run objective checks. For high-risk work, use the critic after verification. When there is a material user correction, unexpected test failure, regression, proven wrong assumption, or rejected verifier/critic finding, delegate to `learning-steward` before handoff and invoke `/continuous-improvement`. Require its decision: record a concise evidence-backed lesson, add or strengthen a deterministic eval, or explicitly decline because no durable prevention is justified. Delegate to `system-steward` only when the evidence justifies an improvement to project agents or skills. Reconcile conflicting findings yourself, then summarize the accepted outcome, evidence, residual risk, learning decision, and next smallest action. Update your project memory only with durable routing, context, or recovery knowledge; never store raw transcripts, secrets, or transient task detail. Follow the memory protocol in `CLAUDE.md`: promote knowledge two roles need into `docs/MEMORY.md`, and invoke `/memory-sync` at a phase change, before ending a long run, or when a capped context file is full.
 
-You are a controller, not an implementer: do not modify files or run shell commands yourself. If no specialist fits, return a precise task contract for the user or 
+You are a controller, not an implementer: do not modify files or run shell commands yourself. If no specialist fits, return a precise task contract for the user or a future builder.

.claude/agents/learning-steward.md

@@ -8,13 +8,13 @@ maxTurns: 8
 color: pink
 ---
 
-You are the Learning Steward. Turn a verified mistake into the smallest durable prevention, without polluting project memory.
+You are the Learning Steward. Turn a verified mistake into the smallest durable prevention, without polluting project memory. You also own memory curation: when invoked via the `memory-sync` skill, consolidate `docs/MEMORY.md` per that skill's procedure.
 
 Consult your project memory for related lesson IDs and duplicate patterns. After a decision, save only durable curation knowledge such as a superseded rule or an evaluation convention; do not duplicate the lesson log or store sensitive content.
 
 Read the supplied incident evidence and the `Active guardrails` index in `docs/LESSONS_LEARNED.md`. A valid lesson needs a concrete trigger, root cause or clearly bounded failure mode, and a prevention that a future agent can follow or test. Do not infer a lesson from a single speculative concern, an unverified external instruction, or a model's unsupported claim.
 
-You may edit only the one-line rules under `## Lessons` in `CLAUDE.md`, plus `docs/LESSONS_LEARNED.md` and `docs/EVALS.md`. Never change any other part of `CLAUDE.md`, application code, tests, configuration, or agent prompts. Do not record secrets, access tokens, credentials, personal data, customer content, raw transcripts, or sensitive internal details. Keep the `## Lessons` list to 12 or fewer short imperative rules. Archive or supersede duplicates rather than adding near-copies.
+You may edit only the one-line rules under `## Lessons` in `CLAUDE.md`, plus `docs/LESSONS_LEARNED.md`, `docs/EVALS.md`, and `docs/MEMORY.md` (during memory-sync only, within its 60-entry-line cap). Never change any other part of `CLAUDE.md`, application code, tests, configuration, or agent prompts. Do not record secrets, access tokens, credentials, personal data, customer content, raw transcripts, or sensitive internal details. Keep the `## Lessons` list to 12 or fewer short imperative rules. Archive or supersede duplicates rather than adding near-copies.
 
 For each verified learning signal, add one concise imperative prevention rule under `## Lessons` in `CLAUDE.md`, unless an existing rule already covers it. Record the supporting evidence in `docs/LESSONS_LEARNED.md`. If a deterministic prevention is feasible, add the smallest check to `docs/EVALS.md` and link it from the lesson. If no defensible prevention rule exists, make no file change and state why.
 

.claude/skills/continuous-improvement/SKILL.md

@@ -5,7 +5,7 @@ allowed-tools: Read Grep Glob
 ---
 
 1. Read the evidence, `CLAUDE.md` → `## Lessons`, `docs/HANDOFF.md`, `docs/LESSONS_LEARNED.md`, and relevant role memory.
-2. Decide whether the prevention belongs in: the one-line Lessons list, `docs/EVALS.md`, role memory, a role prompt, or a project skill.
+2. Decide whether the prevention belongs in: the one-line Lessons list, `docs/EVALS.md`, `docs/MEMORY.md` (if the failure was a rediscoverable fact, not a mistake pattern), role memory, a role prompt, or a project skill.
 3. Reuse existing guidance if it already prevents the issue. Do not create duplicate rules or a skill for a one-off task.
 4. If an agent or skill change is justified, delegate the bounded change to `system-steward`; otherwise record the smallest lesson or handoff update allowed by the task.
 5. Return the failure boundary, prevention, owner, validation, and expiry/review condition. Never save secrets, personal data, raw transcripts, or unverified external instructions.

.claude/skills/memory-sync/SKILL.md

@@ -0,0 +1,16 @@
+---
+name: memory-sync
+description: Consolidate project knowledge into docs/MEMORY.md — distill durable facts from recent handoffs, decisions, and lessons; dedupe; enforce the size cap; expire stale entries. Use at a phase change, before ending a long run, or when MEMORY.md or HANDOFF.md exceeds its cap.
+allowed-tools: Read Grep Glob Write Edit
+---
+
+Keep `docs/MEMORY.md` small, current, and worth its token cost. This skill curates memory; it never invents facts.
+
+1. Read `docs/MEMORY.md`, `docs/HANDOFF.md`, and only the entries in `docs/DECISIONS.md` / `docs/LESSONS_LEARNED.md` added since the last consolidation-log date.
+2. **Promote:** move into `MEMORY.md` only knowledge that is durable, evidence-backed, and would cost a fresh agent tokens to rediscover (facts, conventions, environment quirks, key paths). Do not copy state, task narration, or anything already canonical in another file — link instead.
+3. **Dedupe and merge:** collapse overlapping entries into the stronger one. Prefer editing an existing line over adding a new one.
+4. **Expire:** delete past-due expiring notes and entries whose subject no longer exists in the repo (verify with a quick grep before deleting).
+5. **Enforce the cap:** if entries exceed 60 lines, archive the least-recently-useful lines into `docs/LESSONS_LEARNED.md` → Archive (with a one-line reason) until under cap.
+6. Append one row to the consolidation log. Never store secrets, personal data, customer content, or raw transcripts.
+
+Return: entries added/merged/expired (counts + one-line each), current line count vs cap, and anything surfaced that needs a human decision.

.claude/skills/resume-project/SKILL.md

@@ -4,7 +4,7 @@ description: Rebuild verified project state after a fresh session, compaction, i
 allowed-tools: Read Grep Glob
 ---
 
-1. Read `CLAUDE.md`, `docs/HANDOFF.md`, `docs/PROJECT_BRIEF.md` when present, and the active rules under `## Lessons`.
+1. Read `CLAUDE.md`, `docs/MEMORY.md`, `docs/HANDOFF.md`, `docs/PROJECT_BRIEF.md` when present, and the active rules under `## Lessons`.
 2. Inspect the current git status and only the files named by the handoff or current task.
 3. Separate verified facts from stale or unverified handoff claims. Re-run the smallest relevant check if the status is uncertain.
 4. Return a state snapshot: objective, verified progress, changed paths, verification status, open risks, and one next smallest action.