Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/iampawan/manifest/agents-mdgit clone --depth 1 https://github.com/iampawan/ManifestWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/iampawan/manifest/agents-md)<a href="https://agentmods.dev/instructions/iampawan/manifest/agents-md"><img src="https://agentmods.dev/badge/instructions/iampawan/manifest/agents-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01634 | $0.01634 |
| Opus 5 | $0.00817 | $0.00817 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
Manifest AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed 7f7c07e3dd56
- 4d ago First seen · 157 lines · 1,634 tokens per session scan A 1705895f8256
Manifest AGENTS.md is an instructions file published in the GitHub repository iampawan/Manifest (5 stars, last pushed yesterday), licensed MIT. It adds 1,634 tokens to every session, about $0.0082 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.