Borrowing it
Nothing to install: this file belongs to conorbronsdon/repo-audit. 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/conorbronsdon/repo-audit/main/AGENTS.mdgit clone --depth 1 https://github.com/conorbronsdon/repo-auditWrote 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/conorbronsdon/repo-audit/agents-md)<a href="https://agentmods.dev/instructions/conorbronsdon/repo-audit/agents-md"><img src="https://agentmods.dev/badge/instructions/conorbronsdon/repo-audit/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 5.1 | $0.00807 | $0.00807 |
| Opus 5 | $0.00404 | $0.00404 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
repo-audit 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository guidance for coding agents. SKILL.md is the product; everything else supports it.
What this repo is
One agent skill, SKILL.md, that audits a repository before it goes public. There is no build, no test suite, and no runtime — the skill is the deliverable, and it is read by an agent rather than executed.
Rules
Each rule names the mechanism that checks it, or is marked unenforced. This repo holds itself to its own Step 3 gate.
| Rule | Enforced by |
|---|---|
SKILL.md frontmatter must keep name, description, version, license, compatibility, and metadata |
Unenforced. No validator here yet — check by hand until one exists. |
version in SKILL.md matches the top heading in CHANGELOG.md |
Unenforced. Bump both in the same commit. |
| Line endings are LF | .gitattributes (* text=auto eol=lf), applied by git on commit |
| No credentials or private-context strings | Unenforced in CI. The two-pass scan in SKILL.md Step 4 is run by hand before any public flip. |
| Funding metadata belongs only on this owned repo, never a fork | Unenforced. Convention only. |
If you add a CI gate for any of these, move the row and say what fails closed.
Changing the skill
- Keep the credit to Nnenna Ndukwe in
SKILL.mdandREADME.md. The structure is adapted from her Apache-2.0 work, so removing the attribution while keeping the structure breaks the licence terms. - Worked examples must stay real. Every example in
SKILL.mddescribes something that actually happened. Do not add an illustrative one that did not. - Do not add prose-style checks. This skill owns facts, enforcement, and policy; a writing-quality pass is a separate tool. A second hype-word list here is drift, not a feature.
- Keep the product-shape exception. Removing it makes the skill misfire on games and consumer apps.
Deliberately not here
The launch packs for this repo are Core, Open source, Safety gates, and Distribution. These items in them are skipped on purpose, so an audit does not re-file them:
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 · 43 lines · 807 tokens per session scan A a52596c490f1
repo-audit AGENTS.md is an instructions file published in the GitHub repository conorbronsdon/repo-audit (3 stars, last pushed 9d ago), licensed Apache-2.0. It adds 807 tokens to every session, about $0.0040 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
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).
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.
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).
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.