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/nrwl/metaharness.tools/agents-mdgit clone --depth 1 https://github.com/nrwl/metaharness.toolsWrote 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/nrwl/metaharness.tools/agents-md)<a href="https://agentmods.dev/instructions/nrwl/metaharness.tools/agents-md"><img src="https://agentmods.dev/badge/instructions/nrwl/metaharness.tools/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 | $0.00478 | $0.00478 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
metaharness.tools 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 5d ago.
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.
What it actually says
AGENTS.md
Cursor Cloud specific instructions
This is an Nx monorepo (Astro + Tailwind v4 + React 19) for the metaharness.tools marketing/educational site. Node 22 (.nvmrc) and pnpm 11 are required. The update script runs corepack enable pnpm + pnpm install --frozen-lockfile, so dependencies are already installed before an agent starts.
Two runnable pieces (both dev servers, see README.md and package.json for the canonical commands):
| Piece | What it is | Dev command | URL |
|---|---|---|---|
apps/website |
Astro static site (the product) | pnpm dev (nx dev website) |
http://localhost:4321/ |
packages/animations |
Canvas animations, developed in isolation | pnpm storybook (nx storybook animations) |
http://localhost:6006/ |
Checks / build (what CI runs is nx affected -t check build):
- Type-check website:
pnpm exec nx check website(runsastro check). - Type-check animations:
pnpm exec nx typecheck animations(runstsc --noEmit). - Build website:
pnpm exec nx build website→ output inapps/website/dist.
Non-obvious notes:
- pnpm resolves to v11 via Corepack (driven by
packageManagerDependenciesinpnpm-lock.yaml). If a shell reports pnpm 10.x, runcorepack enable pnpmfirst; installs still succeed on 10 (lockfile is v9.0) but the repo targets 11. - There is no ESLint config and no
lintscript;nx check/typecheckare the type-safety gates.prettier --check .currently reports pre-existing formatting warnings in several files and is not wired into CI — do not mass-reformat. - The website build is affected by the
COMING_SOONenv var (seenetlify.tomlandapps/website/package.jsonnxbuild.inputs). It is unset in local dev, which renders the full site.
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.
- 5d ago First seen · 25 lines · 478 tokens per session scan A aab72d0e5be6
metaharness.tools AGENTS.md is an instructions file published in the GitHub repository nrwl/metaharness.tools (26 stars, last pushed 11d ago), licensed MIT. It adds 478 tokens to every session, about $0.0024 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 2026-08-30.
Other instructions, from other repositories
nightshift AGENTS.md
AGENTS.md instructions for orwa-mahmoud/nightshift: AI-assisted contributions are welcome. The same correctness, security, licensing, testing, and quality standards apply regardless of which tools are used.
KDD AGENTS.md
AGENTS.md instructions for MauricioPerera/KDD: Este repositorio usa la metodología KDD (Knowledge-Driven Development). Las reglas obligatorias completas están en .agents/AGENTS.md y la skill local en .agents/skills/kdd-okf-ccdd-hybrid/SKILL.md.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
lumen AGENTS.md
AGENTS.md instructions for ory/lumen, covering agents.md, repository expectations and commands.
ai-auto-work CLAUDE.md
Claude Code instructions for chaohong-ai/ai-auto-work, covering gamemaker - ai native 游戏创作平台, 项目简介, ai 工作目录约定 and 按需加载（不默认装载）.
catalyst AGENTS.md
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.