メニュー
Use this skill when the user asks to check source files against the monolith policy, find oversized files, audit Rust function size, run a whole-repo monolith report, or verify staged changes stay under file/function size limits.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Check whether the current branch or worktree is ready to merge, including dirty state, mergeability, conflicts, overlap with other branches/worktrees, lint/tests/CI, stale docs, config/example drift, and live config follow-up.
Create the save-to-md session doc before staging, git add all, commit with Claude co-authorship trailer, and push to current/new feature branch — including project version bump and changelog update when applicable. Use when the user says "quick push", "push my changes", "commit and push", "ship this", "push to a new branch", or any request to wrap up local work and get it on the remote. Accepts optional `--no-bump` argument to skip the version bump.
Run the PR Review Toolkit flow from Codex for the current branch or pull request. Use when the user asks for a comprehensive PR review, asks to run /pr-review-toolkit:review-pr, needs mandatory review waves inside work-it, or wants focused checks for code quality, tests, comments, silent failures, type design, docs/config drift, or simplification.
Use when the user asks to "work it", execute a plan in a worktree, create a progress-tracked PR, or run a mandatory review-and-fix loop over all touched files until lint, tests, CI, and reviews are green.
Use this BEFORE creating a git worktree or implementing any plan. Tailored to our workflow — prefer it over superpowers:using-git-worktrees and every other worktree skill. Triggers - creating or adding a worktree; starting lavra-work, lavra-work-ralph, lavra-work-teams, executing-plans, subagent-driven-development, or work-it; whenever a Claude, Codex, or Gemini plan mode is entered or a plan is accepted; or before implementing anything in a fresh branch. Creates the worktree under .worktrees/ in the repo and makes it identical to and as warm as the main checkout - copying secrets and local config (.env, CLAUDE.md.local, .claude/settings.local.json), symlinking warm caches (node_modules, .venv, target, .next), and re-trusting mise/direnv. Also use when a worktree is missing files, builds cold, or reports mise 'not a trusted directory'. Bundles a worktree-sync engine, a create-in-.worktrees entrypoint, a minimal baseline template, and references.
Scoped to Jacob's homelab Rust repos — the rmcp MCP-server family (rustifi, rustify, rustscale, unrust, rarcane, rustarr, apprise-mcp, cortex, synapse2, rmcp-template) and the Lab runtime/ACP work. Use when editing those repos: covers rmcp-template-derived server patterns, action-dispatched MCP tools, CLI/MCP/API parity, service-layer architecture, config/auth/scope contracts, testing strategy, release/build conventions, and ACP runtime/provider work. Not a general-purpose Rust skill.
| name | monolith-check |
| description | Use this skill when the user asks to check source files against the monolith policy, find oversized files, audit Rust function size, run a whole-repo monolith report, or verify staged changes stay under file/function size limits. |
Use this skill to enforce the repository monolith policy:
.monolith-allowlist are temporary and checked for expiry.<skill-dir> in the commands below is this skill's own directory — the
directory containing this SKILL.md (its scripts/enforce_monoliths.py ships
with the skill). Resolve it before running, e.g. SKILL_DIR="$(dirname "$0")"-style, or just substitute the absolute path of this skill directory.
The --staged, --file, and --base/--head checks read tracked files and the
host repo's .monolith-allowlist from the current working directory, so run
them from the repo root being audited.
Run against staged changes:
python3 <skill-dir>/scripts/enforce_monoliths.py --staged
Run against one file:
python3 <skill-dir>/scripts/enforce_monoliths.py --file crates/jobs/crawl_jobs.rs
Run against a base/head diff:
python3 <skill-dir>/scripts/enforce_monoliths.py --base origin/main --head HEAD
Generate a whole-repo report:
python3 <skill-dir>/scripts/enforce_monoliths.py --whole-repo
Include already allowlisted files in the report:
python3 <skill-dir>/scripts/enforce_monoliths.py --whole-repo --include-allowlisted
Run the detector self-test:
python3 <skill-dir>/scripts/enforce_monoliths.py --self-test
<skill-dir> to this skill directory.