agentmods.dev

mcptoon: Instructions file for Codex

AGENTS.md

mcptoon AGENTS.md is an instructions file for Codex, OpenCode from activeing123/mcptoon. It costs 4,636 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for agents working on mcptoon. They define coding, testing, dependency, Windows compatibility, commit, and release rules for that project.

In plain words
What is it for?
They are for guiding development and release work on mcptoon, including running its tests, keeping it dependency-free, supporting Windows, and using Conventional Commits.
Why use it?
They make important project requirements explicit before an agent changes code or publishes a release. This helps avoid broken builds, missing tests, incompatible behavior, or improperly formatted commits.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is activeing123/mcptoon's own configuration. It tells Codex and OpenCode how to work on mcptoon itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcptoon configures →

not rated 422repo +13 changed 6d ago A scan 4,636 tokens original Apache-2.0
View source ↗ activeing123/mcptoon mcptoon.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to activeing123/mcptoon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/activeing123/mcptoon/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/activeing123/mcptoon

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 mcptoon AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/activeing123/mcptoon/agents-md/github.svg)](https://agentmods.dev/instructions/activeing123/mcptoon/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/activeing123/mcptoon/agents-md"><img src="https://agentmods.dev/badge/instructions/activeing123/mcptoon/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.

agentmods 80×15 button for mcptoon AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/activeing123/mcptoon/agents-md"><img src="https://agentmods.dev/badge/instructions/activeing123/mcptoon/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,636 This file is loaded in full into every session.
When invoked 4,636 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04636 $0.04636
Opus 5.5 $0.01854 $0.01854
Sonnet 5.5 $0.00927 $0.00927
Haiku 4.5 $0.00464 $0.00464

Measured 6d ago against content hash 5d10b20ab30a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcptoon 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 6d 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 · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — rules for AI agents working on mcptoon

Any AI agent (Codex, Claude Code, Cursor, DSH, ...) writing code, docs, or cutting releases in this repo follows the rules on this page. They exist because mcptoon is now carried by external automation: numtide/llm-agents.nix packages this project and an official bot auto-bumps it on every PyPI release. A careless release breaks that channel; these rules keep it clean. Human contributors: see CONTRIBUTING.md.

Hard rules

  1. Zero dependencies, always. The dependencies field in pyproject.toml stays empty. Standard library only. CI enforces this via scripts/check_zero_deps.py — treat a red zero-deps job as a broken build, not a suggestion.
  2. Tests gate every change. New behavior ships with tests in tests/. Run python -m pytest tests/ and paste the real green output before claiming done.
  3. Windows is a first-class target. Anything touching paths, subprocess, or npx must work on Windows; the CI matrix runs it on every PR.
  4. Conventional Commits for every commit (feat:, fix:, docs:, test:, chore:).

Release discipline

A release is complete only when all five land together:

  1. version bumped in pyproject.toml
  2. CHANGELOG.md entry written for the new version
  3. full test suite green
  4. git tag vX.Y.Z pushed
  5. PyPI publish green (.github/workflows/publish.yml)

The numtide bot turns PyPI releases into Nix bump PRs automatically. A version that exists on main but not on PyPI (or the reverse) leaves a broken bump in that channel. Breaking changes must land as deprecation warnings one minor version before removal.

Release notes are in English (added 2026-10-04)

The GitHub Release title and body are English — always. The body is the CHANGELOG.md block for that version, verbatim; the title is vX.Y.Z — <short English summary>. Do not paste a commit subject into the title, and do not hand-write a translated body.

Why this is a rule and not a preference: the Release is a global surface. The numtide packaging bot and its maintainers, the PyPI project page (which renders this body), the MCP Registry, Glama's reviewers and every upstream PR author read it. The Chinese-facing surface already exists and is README.zh-CN.md. Measured drift this rule prevents: v0.8.12 shipped with a Chinese title (the release: commit subject, pasted into name) and v0.8.11 with a fully Chinese body that was never in CHANGELOG.md at all — 2 of 47 releases, both fixed 2026-10-04. CHANGELOG.md itself has stayed 0.0% CJK throughout, so following it is enough to stay English; the failure mode is bypassing it.

Read the full file on GitHub · 217 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. 6d ago Changed · +1 lines · +570 tokens per session 5d10b20ab30a
  2. 14d ago Changed · +1 lines · +107 tokens per session 932579a49c57
  3. 19d ago Changed · +11 lines · +219 tokens per session 6cf28f19716d
  4. 25d ago Changed · +31 lines · +459 tokens per session 8001fe04b84c
  5. 1mo ago Changed · +15 lines · +267 tokens per session 3b11ce7a55fe
  6. 1mo ago Changed · +26 lines · +546 tokens per session ecd90111fdaa
  7. 1mo ago Changed · +38 lines · +843 tokens per session 9034423f9599
  8. 1mo ago Changed · +1 lines · +32 tokens per session c79a896428cb
  9. 1mo ago Changed · +1 lines · +31 tokens per session 3f8cce0889df
  10. 1mo ago First seen · 92 lines · 1,562 tokens per session scan A 44242261a715

Subscribe to this mod's changes

mcptoon AGENTS.md is an instructions file published in the GitHub repository activeing123/mcptoon (422 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,636 tokens to every session, about $0.0185 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 2026-09-06.

Claude CodeCommitsGit and workflowTestingclaudecodexcursormcpmcp-client
Related

mcptoon AGENTS.md compared with instructions from other repositories

mcptoon AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcptoon AGENTS.mdactiveing123/mcptoonInstructions file4222d agoApache-2.0A4,636Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode