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/enthouan/trello-mcp/agents-mdgit clone --depth 1 https://github.com/enthouan/trello-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/enthouan/trello-mcp/agents-md)<a href="https://agentmods.dev/instructions/enthouan/trello-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/enthouan/trello-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 | $0.03378 | $0.03378 |
| Opus 5 | $0.01689 | $0.01689 |
| Sonnet 5 | $0.00676 | $0.00676 |
| Haiku 4.5 | $0.00338 | $0.00338 |
Grade A, and why
trello-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 today.
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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file gives coding agents project-specific instructions for this repository. It applies to the entire repo unless a more specific AGENTS.md is added in a subdirectory.
Project Summary
trello-mcp is a self-hostable Model Context Protocol server for Trello. It exposes Trello operations as MCP tools and supports:
- Streamable HTTP MCP transport for container/server deployments.
- stdio MCP transport for local process-based clients.
- Trello API key + token authentication.
- Zod validation for config, tool input, and Trello API responses.
- Pino logging with secret redaction.
- Vitest tests and Biome formatting/linting.
- Docker image publishing through GitHub Actions.
This project is still early, but it has a meaningful public tool surface. Keep changes focused and avoid speculative architecture.
Hard Constraints
- Do not log Trello credentials, request URLs containing credentials, raw environment objects, or full query strings that include auth.
- Do not make live Trello API calls in tests. Use injected fetchers/mocks.
- Do not bypass Zod validation for tool inputs or Trello API responses.
- Keep
src/trello/client.tsas the only place that performsfetchcalls to Trello. - Keep generated/build output such as
dist/, coverage output, andnode_modules/out of commits.
Runtime And Package Manager
- Node.js:
>=24.0.0 <25.0.0. - Package manager:
[email protected]through Corepack. - Module system: ESM (
"type": "module"). - TypeScript is strict, with
exactOptionalPropertyTypesandnoUncheckedIndexedAccessenabled.
Use:
corepack enable
corepack prepare [email protected] --activate
corepack pnpm install --frozen-lockfile
When pnpm-lock.yaml exists, CI/Codex setup should use frozen installs.
Common Commands
Run these from the repository root:
corepack pnpm install --frozen-lockfile
corepack pnpm typecheck
corepack pnpm lint
corepack pnpm build
corepack pnpm test
corepack pnpm test:coverage
corepack pnpm docs:check
corepack pnpm website:typecheck
corepack pnpm website:build
corepack pnpm website:contracts
corepack pnpm website:test
corepack pnpm website:lighthouse
corepack pnpm website:check
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.
- today Changed f181106dda82
- 4d ago First seen · 332 lines · 3,378 tokens per session scan A c9e63d30d724
trello-mcp AGENTS.md is an instructions file published in the GitHub repository enthouan/trello-mcp (4 stars, last pushed today), licensed MIT. It adds 3,378 tokens to every session, about $0.0169 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
CaddyUI-MCP AGENTS.md
Instructions for loryanstrant/CaddyUI-MCP, covering agents.md — caddyui-mcp, project, how to work here, layout and build / test / deploy.
CaddyUI-MCP copilot-instructions.md
Instructions for loryanstrant/CaddyUI-MCP: MCP server (Python 3.13 + FastMCP v3) wrapping CaddyUI's /api/v1 REST API. See AGENTS.md for the full picture; this file mirrors the rules that must hold for inline completions.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
better-notion-mcp AGENTS.md
AGENTS.md instructions for n24q02m/better-notion-mcp, covering agents.md - better-notion-mcp, build / lint / test commands, run a single test file, run a single test by name and mise shortcuts.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
mistral-mcp CLAUDE.md
Instructions for Swih/mistral-mcp, covering claude.md — mistral-mcp, 1. identité du projet, 2. règles dures (ne pas transgresser), 3. layout & responsabilités and 4. conventions de code.