apply
Set chaff up in the folder: chaff.yaml for the chosen genre, today's findings shelved in .chaff-baseline.json, and, when asked, a…
Find the repository's own gates — install, format check, lint, typecheck, build, test — record them, and prove they all pass before anything is touched.
$ npx -y skills add receptron/mulmoterminal --skill baseline --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/baselineContext preview
The summary Claude sees to decide when to auto-load this skill.
Find the repository's own gates — install, format check, lint, typecheck, build, test — record them, and prove they all pass before anything is touched.
name: blueprint-repo-baseline description: "Find the repository's own gates — install, format check, lint, typecheck, build, test — record them, and prove they all pass before anything is touched."
Every later change claims "this behaves the same". That claim is measured against these gates, so they must be the repository's own, and they must be green on the untouched code. A gate that is already red cannot tell a regression from the state it was in.
1. **Package manager** from the lockfile: `yarn.lock` → yarn, `pnpm-lock.yaml` → pnpm, `package-lock.json` → npm, `bun.lockb`/`bun.lock` → bun. The install command must not rewrite the lockfile: `yarn install --frozen-lockfile`, `pnpm install --frozen-lockfile`, `npm ci`, `bun install --frozen-lockfile`. 2. **Gates** from `package.json` scripts, in this order when present: a format CHECK (`format:check`, never a script that rewrites files), `lint`, `typecheck`, `build`, `test`. Read what each script runs.
(`test:e2e` and the like), and write why in the record.
lacks is worth noting. 3. Write `.blueprint/gates.json`:
{
"packageManager": "yarn",
"install": "yarn install --frozen-lockfile",
"gates": [{ "name": "lint", "command": "yarn lint" }, { "name": "test", "command": "yarn test" }],
"skipped": [{ "name": "test:e2e", "why": "needs a browser download" }]
}`name` is the script name exactly as `package.json` has it. 4. Run the install, then every gate, and read each exit code — never the last line of output. 5. If any gate is red on the untouched code, **ask**: it is the person's decision whether to fix it first (as its own change) or leave that gate out with a reason. Do not change the repository in this step.
Done when the check passes: every recorded gate exits 0 on the untouched default branch.
Run multiple coding-agent sessions in parallel — and see which one needs you. A browser terminal for parallel AI coding agents: several sessions side by side, each in its own cell, with the one that needs you marked in colour.
Set chaff up in the folder: chaff.yaml for the chosen genre, today's findings shelved in .chaff-baseline.json, and, when asked, a…
Measure what chaff reports on the named documents today, as the kind the person chose, and propose the setup — changing nothing…
Answer each question from the named documents only, quoting where the answer is written, or saying plainly that the documents do…
Add the approved answers to FAQ.md when the person chose to keep them, after what it already holds; change nothing otherwise.
Build the spec's operations as the Worker's API, with validation and tests.