Borrowing it
Nothing to install: this file belongs to elfa-ai/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/elfa-ai/mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/elfa-ai/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/elfa-ai/mcp/agents-md)<a href="https://agentmods.dev/instructions/elfa-ai/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/elfa-ai/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/elfa-ai/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/elfa-ai/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 | $0.00354 | $0.00354 |
| Opus 5.5 | $0.00142 | $0.00142 |
| Sonnet 5.5 | $0.00071 | $0.00071 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
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 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.
This is a copy
100% identical to skills AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
AGENTS.md
Guidance for AI coding agents working in this repository. CLAUDE.md imports this file; keep guidance here.
This repository is public
Everything here is world-readable and permanent: code, comments, commit messages, branch names, PR titles and descriptions, review replies and issue comments. Forks and archives keep copies after a force-push, and GitHub keeps every earlier version of an edited PR description where anyone can read it. So never write any of the following, in the repo or on GitHub:
- names of Elfa's private repositories, or links to their PRs, issues or commits (
org/repo#123,repo#123, URLs) - internal service names or codenames. Name the public thing instead: "the API", "Auto", "the published spec", "docs.elfa.ai"
- paths into private source code, internal hostnames, staging or preview URLs
- teammates' names in prose, internal threads or decisions ("X confirmed in-thread"). A
Co-authored-by:trailer crediting a contributor is fine and must be kept - anything not yet live on docs.elfa.ai: unreleased, flag-gated or staging-only work
- deployment, infrastructure, incident or business detail
- secrets, local machine paths, personal editor or agent config (
.mcp.json,.claude/)
To say where a change came from, cite the public source ("matches the spec published on docs.elfa.ai"), not the internal change behind it. Before pushing, reread the diff, commit messages and PR description as an outsider would. If a sentence would tell a competitor something about how Elfa builds software, cut it.
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 · 18 lines · 354 tokens per session scan A 7dfdfaa7c20c
mcp AGENTS.md is an instructions file published in the GitHub repository elfa-ai/mcp (7 stars, last pushed yesterday), licensed MIT. It adds 354 tokens to every session, about $0.0014 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to skills AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.