Manifest: Instructions file for Codex

AGENTS.md — Manifest

Manifest takes a PRD from spec → build → launch with quality gates. Version 0.43.0.

Works in any agent. The gates are plain Node, so Codex, Cursor, Gemini CLI, Copilot, Aider, Windsurf, Zed and CI all get identical results. A gate code minted in one tool verifies in every other — it's a content hash, not a model judgement.

Ready Check needs nothing installed. scripts/ready-check.mjs is a single file with zero dependencies — Node 18+ and that one file is the whole PM-side gate. (Only the contract/repo tooling — validate.mjs, build-code-context.mjs — needs js-yaml: cd scripts && npm install.)

---

The one rule

Never hand-write a Ready Check hand-off, scorecard, or gate code. Always run the CLI and use its output verbatim. A hand-written block looks official and proves nothing — --verify reports UNVERIFIABLE because the • [id] … item list it hashes isn't there. Same for the score: run --scorecard, don't estimate it.

---

Ready Check — the PM gate (before dev grooming)

Score a PRD against the Definition of Ready, then mint a tamper-evident hand-off.

node scripts/ready-check.mjs --scorecard answers.json     # panel-like status
node scripts/ready-check.mjs --check     answers.json     # verdict JSON (exit 1 if not ready)
node scripts/ready-check.mjs --handoff   answers.json freeze.json   # hand-off + freeze stamp

answers.json:

{ "title": "<feature>",
  "items": {
    "goal":   { "detail": "..." },
    "design": { "na": true, "reason": "why it genuinely doesn't apply" },
    "metric": { "waived": true, "reason": "why it can't be answered yet" }
  } }

Workflow: read the PRD (fetch the link if you can) → map it to the items below → run --scorecard → show it → ask only for the gaps → fold the replies in → re-run until it clears → then --handoff.

The 11 required items