Borrowing it
Nothing to install: this file belongs to P4ST4S/mcp-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/P4ST4S/mcp-audit/main/CLAUDE.mdgit clone --depth 1 https://github.com/P4ST4S/mcp-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/p4st4s/mcp-audit/claude-md)<a href="https://agentmods.dev/instructions/p4st4s/mcp-audit/claude-md"><img src="https://agentmods.dev/badge/instructions/p4st4s/mcp-audit/claude-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 | $0.00582 | $0.00582 |
| Opus 5 | $0.00291 | $0.00291 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
mcp-audit CLAUDE.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 8d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
Claude Code specific
The instructions above apply to all agents. Below are notes specific to Claude Code sessions on this repository.
Working directory
Run Claude Code from the repo root. The build, test, and lint commands in AGENTS.md assume this.
Verification reflexes the maintainer values
When you make a non-trivial code change, the maintainer expects you to verify it concretely before claiming it's done:
- Run
go build ./...after touching Go code - Run
go test -race ./...for any change that touchesinternal/ - For changes to
cmd/mcp-audit/orinternal/proxy/, run a manual smoke test against the built binary withdemo/config.yamlbefore reporting completion - For test additions, run
go test -shuffle=on -count=3 ./pkg-under-test/...to confirm the test doesn't depend on hidden state
If you skip verification, say so explicitly ("I haven't run the smoke test because X") rather than implying it passed.
Plan mode for surface changes
Use plan mode (EnterPlanMode) before changes that touch:
- The stable surface listed in STABILITY.md: config keys, CLI flags, audit JSON schema, the signed field set, Prometheus metric names, OTLP
mcp_audit.*attributes, dashboard API endpoints, or JSON-RPC error codes - Concurrency-sensitive code in
internal/audit/storage/(the SQLite mutex and the async-store closeMu lock both fix real prior bugs; touching them without a plan is risky) - Anything in
cmd/mcp-audit/main.gothat affects startup ordering or signal handling
For pure additions in internal/ packages (new tests, new feature flag wired through the existing pattern), plan mode is optional.
When asked to draft text the maintainer will post publicly
Some output here is destined for GitHub comments, Discord messages, or LinkedIn posts. House style:
- Never use the em-dash character. Use commas, periods, or split the sentence.
- Never use "we" when speaking on the maintainer's behalf — he is solo on this project.
- Never say "Welcome to open source" or similar paternalistic greetings to contributors. Treat them as peers.
- Don't post "thanks for the thanks." Once is enough.
- If the message adds no new information, suggest an emoji reaction (👍 🎉 👀) instead of a comment.
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.
- 8d ago First seen · 45 lines · 582 tokens per session scan A 159dd6fd49a0
mcp-audit CLAUDE.md is an instructions file published in the GitHub repository P4ST4S/mcp-audit (7 stars, last pushed today), licensed Apache-2.0. It adds 582 tokens to every session, about $0.0029 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.