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/paladini/mcp-me/agents-mdgit clone --depth 1 https://github.com/paladini/mcp-meWrote 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/paladini/mcp-me/agents-md)<a href="https://agentmods.dev/instructions/paladini/mcp-me/agents-md"><img src="https://agentmods.dev/badge/instructions/paladini/mcp-me/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 | $0.01218 | $0.01218 |
| Opus 5 | $0.00609 | $0.00609 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
mcp-me 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
This file provides instructions for AI coding agents (Copilot, Cascade, Cursor, Cline, etc.) working on this project.
Critical Rules
-
Always verify before declaring done — Before saying a task is complete, committing, or pushing, you must run the full verification suite in this exact order:
npm run lint # ESLint must pass with 0 errors npm run typecheck # TypeScript strict mode, no errors npm test # All Vitest tests must pass npm run build # tsup build must succeedIf any step fails, fix the issue before proceeding. Never commit or push broken code.
-
Always update
CHANGELOG.md— Every change, no matter how small, must be documented under[Unreleased]following Keep a Changelog format. -
Always update documentation — If your change affects user-facing behavior, update
README.md,docs/creating-plugins.md,docs/schema-reference.md, and any other relevant docs. -
Follow Semantic Versioning — Bump the version in
package.jsonwhen preparing a release:- PATCH (0.1.x): Bug fixes
- MINOR (0.x.0): New features, new plugins
- MAJOR (x.0.0): Breaking changes to plugin interface or schema
-
Use Conventional Commits — Format:
feat:,fix:,chore:,docs:,refactor:,test:. -
Add tests for every change — New features and bug fixes must include tests. Never reduce test coverage.
-
No unused imports — ESLint enforces this. Clean up imports when refactoring.
-
Plugin changes require plugin docs — Any change to a built-in plugin must update its
README.md. Any change to the plugin interface must updatedocs/creating-plugins.md.
Pre-commit Checklist
Before every commit, verify:
-
npm run lintpasses (0 errors) -
npm run typecheckpasses (0 errors) -
npm testpasses (all tests green) -
npm run buildsucceeds (ESM + DTS) -
CHANGELOG.mdis updated - Documentation is updated (if behavior changed)
- Commit message follows Conventional Commits
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 · 102 lines · 1,218 tokens per session scan A 71b90b2b0e1f
mcp-me AGENTS.md is an instructions file published in the GitHub repository paladini/mcp-me (18 stars, last pushed 24d ago), licensed MIT. It adds 1,218 tokens to every session, about $0.0061 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 2026-08-30.
Other instructions, from other repositories
inspecto CLAUDE.md
Claude Code instructions for inspecto-dev/inspecto, covering inspecto — claude code development guide, project overview, monorepo structure, development phases (load each file as needed) and key architectural decisions.
ChatCCC AGENTS.md
AGENTS.md instructions for wzj998/ChatCCC, covering 协作原则（核心）, 开发注意点 and 日志位置.
Dex CLAUDE.md
Claude Code instructions for davekilleen/Dex, covering dex - your personal knowledge system, first-time setup, user profile, reference documentation and user extensions (protected block).
mcp-quickstart AGENTS.md
Instructions for G12789/mcp-quickstart, covering agents.md, what this project is, layout, conventions and how to test changes.
Dex AGENTS.md
AGENTS.md instructions for davekilleen/Dex, covering working on dex-core (agent instructions), communicating with the founder, github access in managed codex runners, orient before you touch anything and merged is not shipped, and shipped is not always live.
jobs-mcp-proxy CLAUDE.md
Claude Code instructions for foundrole/jobs-mcp-proxy, covering claude.md - jobs mcp proxy project development rules, project overview, package manager, ✅ correct and ❌ incorrect.