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

docs/HANDOFF.md

@@ -19,6 +19,7 @@
   - `entrypoints/content.ts` — fixed unbounded document-listener leak: `showToolbar` added `click`/`scroll` listeners per selection and never removed them; now unregistered in `hideToolbar` (also closes an orphaned More-menu). Error toast gained `data-lexai`; mouseup threshold now uses `MIN_SELECTION_LENGTH` (was hardcoded `<= 10`, which ate exactly-10-char selections); same sender guard on its listener.
   - `src/lib/providers.ts` — `callProvider` guards `res.json()` so non-JSON gateway errors (HTML 502) surface as `"<Provider> error: HTTP <status>"` instead of a raw SyntaxError.
   - Verified: typecheck clean, 54/54 tests (6 new: 4 migration, 1 non-JSON error, plus existing), build clean (280.3 kB). `security-auditor` reviewed the key-path diff: PASS; its two P3 hardening notes (await encKey persistence, concurrent-save re-check) were implemented and re-gated. User-text privacy audited clean: no persistence of analyzed text, debug logs dev-gated, key/text travel only to the chosen provider. Real-page load-unpacked check of toolbar/replace still recommended (DOM-timing paths untouched except listener cleanup).
+- **CI fix + workflow hardening (2026-07-15):** CI typecheck failed on push (`content.ts(10,31) TS2339: Property 'env' does not exist on type 'ImportMeta'`) because `.wxt/types/` (which types `import.meta.env`) is generated by `wxt prepare`, which CI never ran — locally it existed as a side effect of `wxt build`/`dev`. Reproduced locally by deleting `.wxt/`. Fixes: `postinstall: wxt prepare` in package.json (root fix — every fresh install regenerates types); explicit "Prepare WXT types" step in both workflows (survives a future `--ignore-scripts`); `deploy-chrome.yml` now runs **typecheck** before tests (release previously gated less than CI); fixed `head -1` → `sed '$d'` body extraction in both curl-response checks (body is all-but-last-line, not first line); added `timeout-minutes` (15 CI / 20 deploy). Verified: fresh install regenerates `.wxt`, then typecheck + 54/54 tests + build all green. CLAUDE.md Commands section documents the gotcha.
 - **Changed paths (this alignment):** added `docs/` (brief, architecture, decisions, tasks, evals, lessons, handoff, self-model, attacksurface), ported `.claude/agents/*` roster + `.claude/skills/*`, kept `lexai-extension-dev`, updated `.claude/AGENTS.md`. `CLAUDE.md` restructured to the operating-system format (all original LexAI rules preserved).
 - **Open risks (ranked):**
   1. `<all_urls>` host permission — privacy surface + CWS review blocker (TASKS #1).

docs/MEMORY.md

@@ -0,0 +1,49 @@
+# Project memory — LexAI
+
+> Curated long-term knowledge that must survive sessions, compaction, and agent turnover. Loaded at every session start alongside `HANDOFF.md`. **Hard cap: 60 lines of entries.** When full, the `memory-sync` skill consolidates or archives before adding. Facts only — state goes in `HANDOFF.md`, mistakes in `LESSONS_LEARNED.md`, choices in `DECISIONS.md`.
+
+## Verified facts
+
+Durable, evidence-backed truths about this project (domain rules, invariants, external realities).
+
+- No backend: the background service worker is the only context that calls provider APIs; the user's key never leaves the extension except to the chosen provider.
+
+## Conventions
+
+How this codebase does things (naming, structure, patterns a new agent must follow).
+
+- UI is inline style objects (dark Catppuccin-ish palette); Tailwind is installed but inactive.
+- Each provider is duplicated as `callX` + `callXWithPrompt` — change both until T-04 refactors the layer.
+
+## Environment quirks
+
+Non-obvious facts about tooling, commands, CI, or the operator's machine that repeatedly cost time to rediscover.
+
+- `node_modules` is gitignored and absent by default — run `npm install` before any `npm run *`.
+- CI is Gitea (`.gitea/workflows/`), Node 22 pinned. Version must match in `package.json` and `wxt.config.ts`.
+
+## Key paths and entry points
+
+| What | Where |
+| --- | --- |
+| Content script (selection, toolbar, replace) | `entrypoints/content.ts` |
+| Background LLM proxy (providers, key decrypt) | `entrypoints/background.ts` |
+| Options (provider/model/key + encrypt) | `entrypoints/options/Options.tsx` |
+| Popup (standalone analyze) | `entrypoints/popup/Popup.tsx` |
+| Task list (from RECOMMENDATIONS) | `docs/TASKS.md` |
+
+## Expiring notes
+
+Short-lived knowledge with an explicit expiry; `memory-sync` deletes past-due entries.
+
+- _None yet. Format: `[YYYY-MM-DD expires] note`_
+
+## Consolidation log
+
+| Date | Action | Reason |
+| --- | --- | --- |
+| 2026-07-15 | Seeded initial facts, conventions, quirks, key paths | memory layer added |
+
+---
+
+*Write rules: one line per entry, evidence-backed, no secrets/personal data/transcripts. Every entry must answer "would a fresh agent waste tokens rediscovering this?" — if no, it doesn't belong here.*