Borrowing it
Nothing to install: this file belongs to deeprave/mcp-guide. 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/deeprave/mcp-guide/main/AGENTS.mdgit clone --depth 1 https://github.com/deeprave/mcp-guideWrote 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/deeprave/mcp-guide/agents-md)<a href="https://agentmods.dev/instructions/deeprave/mcp-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/deeprave/mcp-guide/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/deeprave/mcp-guide/agents-md"><img src="https://agentmods.dev/badge/instructions/deeprave/mcp-guide/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 | $0.00499 | $0.00499 |
| Opus 5.5 | $0.00200 | $0.00200 |
| Sonnet 5.5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
mcp-guide 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 1mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UK/AU Spelling
You are to use UK/AU spelling in all written text, documentation, symbols, variable, function, comments, file and directory names. But there do exist rare exceptions widely accepted industry spellings such as "license", "artifact" and software colloquialisms.
Guide MCP Response Handling
- Always respect instructions and special_agent_instructions embedded in an MCP response,
- When an MCP Guide response instructs you to present information to the user without interpretation, reproduce the returned information exactly and verbatim (only markdown formatting allowed) - do not paraphrase, abbreviate, interpret, summarise information that MCP Guide instructs you to present verbatim.
- Follow every
additional_agent_instructionsvalue returned by MCP Guide. - If told to
set_project, provide it with the project root directly and immediately.
These rules are critical for MCP operations to work correctly.
Git Commit Safety
- NEVER EVER use
--no-verifyunder any circumstances unless explicitly requested by the user. - Do not bypass commit checks.
- NEVER use
--no-gpg-sign; this is forbidden with no exceptions. - Do not bypass commit signing.
Pytest Execution
- Run every pytest invocation in a foreground terminal, including direct
pytestcommands and indirect invocations through pre-commit orgit commithooks. - Do not run pytest in a background or short-lived execution context; wait for its complete result before proceeding.
Test Quality
- NEVER test the literal content of a production file. Tests MUST validate observable behaviour; source-text assertions against templates, documentation, or other production files are prohibited.
Transient Documentation
- NEVER create execution plans, agent ledgers, reviews, or other transient documentation in the worktree. The configured or default
{{path.documents}}directory is the ONLY allowed location for transient documentation.
Workflow Handover
- After each significant milestone, update
.todo/context.jsonwith the current handover context so work can be resumed reliably by this or another agent. - This is for AI consumption so should be concise but sufficient.
- Together with .guide.yaml this context keeps track of:
- current workflow phase
- issue status
- recently completed work
- remaining work to be done
- any blockers
- immediate expected next action.
- This is not a historical document; remove any item that is no longer relevant whenever the file is updated.
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.
- 1mo ago Changed · +8 lines · +82 tokens per session a378e6189005
- 1mo ago Changed · +19 lines · +246 tokens per session 648ff097d61b
- 1mo ago First seen · 20 lines · 171 tokens per session scan A d411e5d07702
mcp-guide AGENTS.md is an instructions file published in the GitHub repository deeprave/mcp-guide (0 stars, last pushed 2d ago), licensed MIT. It adds 499 tokens to every session, about $0.0020 per session on Opus 5.5. 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
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.