docs(memory): skill-review-loop — supervised delivery loop skill

Claude-Session: https://claude.ai/code/session_018LRh1S2bHJYhEgrMu3UJx8

MEMORY.md

@@ -38,6 +38,7 @@
 - [/ask-minimax-with-context](memory/skill-ask-minimax-with-context.md) — Bundle CONTEXT/CLAUDE.md hierarchy via shell redirects, then ask MiniMax a one-line question
 - [/spawn-session](memory/skill-spawn-session.md) — Spawn a new detached tmux Claude Code session with Remote Control, named after a project (wraps claude-tmux)
 - [/review-minimax](memory/skill-review-minimax.md) — First-pass MiniMax code review of agent branches; findings file adjudicated in-session; pre-filter before /code-review
+- [/review-loop](memory/skill-review-loop.md) — Supervised delivery loop: discover → plan → spec → Sonnet tests → MiniMax worktree code → integrate → deploy → verify live, MiniMax-reviewed at every stage
 - [/ci-triage-minimax](memory/skill-ci-triage-minimax.md) — MiniMax triage of failed Gitea Actions runs via gac; failing step + cause file; after `gac tail` exits 1
 
 ## References

memory/skill-review-loop.md

@@ -0,0 +1,28 @@
+# /review-loop Skill
+
+**Purpose:** Supervised delivery loop for planner-backed projects (agent-runtimes, hatchmate …): verify the item is still real → plan → spec → Sonnet tests → MiniMax code in a worktree → integrate → deploy → verify live, with an independent MiniMax review of every artefact until no CRITICAL/HIGH (cap 4 rounds). Codifies the 2026-09-13 program that shipped WIA-17c..f and PDIV (agent-runtimes item `824222cb` holds every round).
+
+**Location:** `custom-claude-skills/skills/review-loop/SKILL.md`.
+
+## Usage
+
+`/review-loop <uuid> [<uuid> …] [--from discover|plan|spec|tests|code|integrate|deploy]`
+
+Requires: MiniMax profile, `mm-worktree-task` (small-scripts), `ask-minimax-run`, `cp-cli` context for the project, `gac`, cluster access for the deploy stage.
+
+## How it works
+
+- **Roles:** supervisor (the session) adjudicates and gates; MiniMax verifies/reviews; Sonnet subagents write spec-ahead tests (xfail strict); MiniMax implements in its own git worktree via `mm-worktree-task`.
+- **Gates:** spec review clean → tests 0 xpassed / 0 errors → coder branch has an EMPTY `git diff main...branch -- tests/ spec/` → target tests pass with `--runxfail` → MiniMax code review clean → test-merge branch with markers stripped, full suite green → ff main → `[CI BUILD] [DEPLOY]` → reproduce the original bug live → close the item with evidence.
+- **Discovery first:** most "open" planner records are stale; a MiniMax code check with cited evidence closes them before any work is planned.
+
+## Gotchas (learned the hard way)
+
+- Reviewers keep reporting "symbol does not exist" on spec-ahead artefacts — reject that class in the prompt or it eats every round.
+- Launch MiniMax detached via `setsid nohup <script>`; `pkill -f 'MiniMax-M3'` kills the invoking shell. Build prompts with Python, not `sed` (paths contain `/`).
+- A push to main during an in-flight `[CI BUILD]` run cancels it — re-trigger with an empty deploy commit.
+- Ordering bugs (memoised state created before the lifespan wires a dependency) only show in a test that drives `create_app()` + the real lifespan; unit tests with a bare `app_state` pass. Incident `aa98d9fe`.
+- Local `scripts/generate-sdks.sh` churns ~77 files from generator-version drift; revert unless a route/schema changed.
+- git *worktrees*, not subtrees — `mm-worktree-task` creates `.claude/worktrees/mm-<slug>` on branch `mm/<slug>`.
+
+**Used by:** agent-runtimes (first run 2026-09-13); intended for any project with a `cp-cli planner` reference in its CLAUDE.md.