Borrowing it
Nothing to install: this file belongs to marchatton/agent-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marchatton/agent-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/marchatton/agent-skillsWrote 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/marchatton/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/marchatton/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/marchatton/agent-skills/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/marchatton/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/marchatton/agent-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00785 | $0.00785 |
| Opus 5 | $0.00392 | $0.00392 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
agent-skills 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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Tooling
- Package manager: pnpm (workspaces)
- Prefer TypeScript for new code unless the repo already uses something else
Principles
We follow core ideas from The Pragmatic Programmer (Andy Hunt, Dave Thomas):
- Take ownership. If something’s broken/unclear/risky or “not your job”, act anyway: flag it, fix it, or shape a better path.
- Keep learning. Maintain a “knowledge portfolio”. Store learnings in
docs/LEARNINGS.md. - Avoid duplication (DRY). Duplicate knowledge is as bad as duplicate code. Keep one source of truth and reuse it.
- Build orthogonally. Reduce coupling, keep dependencies explicit, and interfaces small.
- Use tight feedback loops. Small steps, fast validation. Use tracer bullets (thin end-to-end slices). One concern per commit/PR. Prefer the simplest thing that meets the requirement.
- Prototype to learn, then bin it (when needed). Don’t let prototypes silently become production.
- Make behaviour explicit. Clear contracts, assert assumptions, fail loudly when they break.
- Automate boring/error-prone work. Builds, tests, formatting, releases, setup, checks. If you do it twice, consider scripting it.
- Keep code easy to change. Refactor continuously, rename aggressively, optimise for readability.
- Debug systematically. Reproduce, isolate, change one thing at a time. Use tools properly.
- Fix broken windows. Small messes spread — tidy early.
- Communicate trade-offs. Requirements/estimates are conversations. Explain options, risks, and costs plainly.
Vibe: be practical, stay curious, optimise for long-term leverage over short-term heroics.
Error handling + safety (high level)
- Validate external inputs at boundaries (Zod) and return safe user-facing errors
- Don’t leak internal errors/details to clients
- Unexpected issues: fail loudly (log/throw). Only show user-facing errors when needed
Compatibility
- Backwards compatibility is usually not required.
- Avoid adding shims/legacy paths for older major versions unless explicitly requested (assume a fresh codebase).
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.
- 7d ago First seen · 52 lines · 785 tokens per session scan A 8ef1cf14aa7b
agent-skills AGENTS.md is an instructions file published in the GitHub repository marchatton/agent-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 785 tokens to every session, about $0.0039 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 2026-09-03.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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.
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).
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.