mcp-doctor AGENTS.md

mcp-doctor AGENTS.md is an instructions file for Codex, OpenCode from Coefficient-work/mcp-doctor. It costs 736 tokens per session, scanned A, original, MIT.

An instruction guide for the Coefficient-work/mcp-doctor repository. It covers choosing between Codex and Cursor, using a remote API for Gmail and Google files, and fetching files between Macs.

In plain words
What is it for?
Use it when working in mcp-doctor, especially for agent-routing decisions, Gmail or Google file operations, remote Mac file retrieval, and related setup or troubleshooting.
Why use it?
It prevents agents from choosing the wrong coding workflow or using prohibited access methods for email and Google Drive, Sheets, or Docs. It also documents the approved route for files stored on another machine.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/coefficient-work/mcp-doctor/agents-md
Clone the repo
git clone --depth 1 https://github.com/Coefficient-work/mcp-doctor

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for mcp-doctor AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/coefficient-work/mcp-doctor/agents-md.svg)](https://agentmods.dev/instructions/coefficient-work/mcp-doctor/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/coefficient-work/mcp-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/coefficient-work/mcp-doctor/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 736 This file is loaded in full into every session.
When invoked 736 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00736 $0.00736
Opus 5 $0.00368 $0.00368
Sonnet 5 $0.00147 $0.00147
Haiku 4.5 $0.00074 $0.00074

Measured 3d ago against content hash a836cff36770, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-doctor 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 3d 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.

AGENTS.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent guide

Repository: mcp-slim

Codex vs Cursor (agent routing)

Use the codex-vs-cursor skill when choosing the coding agent for a job:

  • Cursor — daily IDE (UI, Flutter, Payload admin, TARS ops, fuzzy explore/debug, live diffs)
  • Codex — walk-away / async (scoped migrations, schema PRs, batch fixes, large refactors → PR)

Skill: .cursor/skills/codex-vs-cursor/SKILL.md · re-install: bash /Users/louisreid/Documents/tars/scripts/install-codex-vs-cursor-skill.sh

Prompt: Use codex-vs-cursor. Job: … Repo: … Interactive now or walk-away PR?

TARS remote API (Gmail / Drive / Sheets) — mandatory

Always use tars-remote-api for Louis’s Gmail, Miriam’s Gmail (account:"mim"[email protected]), and Google Drive/Sheets/Docs via Mac mini :3049. Do not use Cursor plugin-gmail / plugin-google-drive or local Google OAuth in this repo.

Skill: .cursor/skills/tars-remote-api/SKILL.md Re-install: bash /Users/louisreid/Documents/tars/scripts/install-tars-remote-api-skill.sh

Cursor secrets (Cloud Agent only): REID_REMOTE_TOKEN, MAC_MINI_HOST, TAILSCALE_AUTH_KEY — not injected in Build Locally.

Preflight: bash /Users/louisreid/Documents/tars/scripts/tars-remote-preflight.sh

Hub: tars cross-repo bridge · google-api README

Prompts:

  • Use tars-remote-api skill. Run preflight, then search Gmail …
  • Use tars-remote-api skill. Run preflight. Search Mim Gmail (account:mim) …
  • Use tars-remote-api skill. Run preflight. Search Drive … (not the Drive plugin)

Cross-machine file fetch (Mini ↔ Air)

When a path is on the other Mac (Mini ↔ Air), use skill cross-machine-fetch (~/.cursor/skills/cross-machine-fetch · .cursor/skills/cross-machine-fetch).

Machine Host alias IP User
Mini mini / roundtableopenclaw 100.84.168.56 roundtableopenclaw
Air air / louiss-macbook-air 100.83.203.72 louisreid

Read the full file on GitHub · 50 lines

Changes

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.

  1. 3d ago First seen · 50 lines · 736 tokens per session scan A a836cff36770

Subscribe to this mod's changes

mcp-doctor AGENTS.md is an instructions file published in the GitHub repository Coefficient-work/mcp-doctor (0 stars, last pushed 10d ago), licensed MIT. It adds 736 tokens to every session, about $0.0037 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.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens