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.
npx agentmods add instructions/wanghehacker/cocos-mcp/agents-mdgit clone --depth 1 https://github.com/wanghehacker/cocos-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/wanghehacker/cocos-mcp/agents-md)<a href="https://agentmods.dev/instructions/wanghehacker/cocos-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wanghehacker/cocos-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00439 | $0.00439 |
| Opus 5 | $0.00219 | $0.00219 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
cocos-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 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.
What it actually says
Repository Guidelines
Project Structure & Module Organization
This repository is currently minimal, with only README.md and LICENSE at the root. There is no established src/, tests/, or assets/ directory yet. When adding code, prefer a clear top-level layout such as:
src/for implementation codetests/for automated testsscripts/for developer utilitiesassets/for non-code artifacts
Build, Test, and Development Commands
No build, test, or run scripts are configured yet. If you add tooling, document the primary commands here (for example: npm run build, npm test, or make dev) and keep the list short and actionable.
Coding Style & Naming Conventions
No formatting or linting rules are defined. If you introduce a language or framework, also add:
- Indentation rules (e.g., 2 spaces for JS/TS, 4 spaces for Python).
- Naming patterns (e.g.,
camelCasefor variables,PascalCasefor types). - Formatting/linting tools (e.g.,
prettier,eslint,ruff) and how to run them.
Testing Guidelines
No test framework is configured. When tests are added, include:
- The framework name (e.g.,
jest,pytest). - Naming conventions (e.g.,
*.spec.ts,test_*.py). - How to run the suite (e.g.,
npm test,pytest).
Commit & Pull Request Guidelines
The git history currently contains only an initial commit, so no commit message convention is established. Keep messages clear and imperative (e.g., "Add README section").
For pull requests, include:
- A concise description of changes and motivation.
- Links to related issues (if any).
- Notes on testing performed (commands and results).
Configuration & Security Notes
No runtime configuration or secrets are defined. If you add configuration files, document where they live (for example, .env.example) and how to manage sensitive values safely.
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.
- 3d ago First seen · 35 lines · 439 tokens per session scan A b1639615b4b0
cocos-mcp AGENTS.md is an instructions file published in the GitHub repository wanghehacker/cocos-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 439 tokens to every session, about $0.0022 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
linkedin-content-engine CLAUDE.md
Claude Code instructions for mdbailin/linkedin-content-engine, covering claude implementation brief, goal, architecture constraints, required mcp tools and readbrandprofile.
carousels GEMINI.md
Instructions for sausi-7/carousels: See AGENTS.md for the full pipeline, commands and file shapes.
docvideoer CLAUDE.md
Instructions for coding-ax/docvideoer, covering claude.md — docvideoer, 触发方式, 外部 skill 依赖, 工作目录 and 核心流水线（6 步）.
ai-workflow-kit CLAUDE.md
Claude Code instructions for bezael/ai-workflow-kit, covering claude.md — ai workflow kit, what this repo is, where each tool reads skills from, available skills and specialized agents.
video-mcp CLAUDE.md
Claude Code instructions for Zoean-z/video-mcp, a project described as: 让agent学会理解视频，无需复杂依赖和额外花费.
glm-image-mcp-server CLAUDE.md
Claude Code instructions for ex-takashima/glm-image-mcp-server, covering claude.md - development guide, project overview, build & run commands, install dependencies and build typescript.