Borrowing it
Nothing to install: this file belongs to dmccaffery/claude-desktop-mcp. 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/dmccaffery/claude-desktop-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/dmccaffery/claude-desktop-mcpWrote 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/dmccaffery/claude-desktop-mcp/agents-md)<a href="https://agentmods.dev/instructions/dmccaffery/claude-desktop-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dmccaffery/claude-desktop-mcp/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/dmccaffery/claude-desktop-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dmccaffery/claude-desktop-mcp/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 | $0.00250 | $0.00250 |
| Opus 5 | $0.00125 | $0.00125 |
| Sonnet 5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
claude-desktop-mcp 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 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.
What it actually says
Agent instructions
Repo-specific conventions for AI agents working in this repository. These layer on top of the global agent instructions
in ~/.claude/CLAUDE.md. CLAUDE.md is a symlink to this file, so Claude Code and any other AGENTS.md-aware tool
read the same guidance.
Before preparing commits
Run make pr before preparing any commit. It runs the full pre-commit gate — license, fmt, lint, and test — so
the working tree is license-headed, formatted, lint-clean, and green before anything is staged.
Then author the commit per the global commit convention: write commit.sh at the repo root (or re-sign inside a
worktree) and hand it to the user to run. make commit depends on pr, so it runs the same gate first and then
executes ./commit.sh when that script is present — making make commit the one-shot path once commit.sh exists.
Never run git commit directly from inside the sandbox: commit signing runs through ssh-agent, which the sandbox
blocks, so any commit made there lands unsigned.
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 · 18 lines · 250 tokens per session scan A bcd526427c6a
claude-desktop-mcp AGENTS.md is an instructions file published in the GitHub repository dmccaffery/claude-desktop-mcp (0 stars, last pushed today), licensed MIT. It adds 250 tokens to every session, about $0.0013 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
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.