agentmods.dev

faf-mcp AGENTS.md

Project instructions for a TypeScript command-line application built with Bun, a JavaScript runtime and toolkit. They describe setup, testing, project locations, coding rules, security limits, and the process for submitting changes.

In plain words
What is it for?
Use them when installing, building, testing, linting, navigating, or changing the faf-mcp project, while following its rules for secrets, branches, commits, and pull requests.
Why use it?
They give a coding agent the repository’s rules in one place, including which commands to run and which files or actions require caution. This reduces inconsistent changes and missed checks.

Instructions file for CodexOpenCode

6 13d ago A scan 369 tokens original MIT
View the source file Wolfe-Jam/faf-mcp
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/wolfe-jam/faf-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/Wolfe-Jam/faf-mcp

Made for: Codex, OpenCode.

Per session 369 This file is loaded in full into every session.
When invoked 369 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 $0.00369 $0.00369
Opus 5 $0.00185 $0.00185
Sonnet 5 $0.00074 $0.00074
Haiku 4.5 $0.00037 $0.00037

Measured 3d ago against content hash 32db35cd60a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

faf-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.

AGENTS.md · 60 lines

What it actually says

AGENTS.md — faf-mcp

TypeScript · CLI · Bun · npm package manager · v2.3.1

Setup & build

npm install    # install dependencies
npm run build    # build
npm run dev    # dev
npm run start    # start

Run the tests

npm run test
npm run lint

Where things live

  • package.json
  • src/index.ts
  • src/cli.ts
  • tests/
  • README.md
  • CHANGELOG.md
  • tsconfig.json
  • vercel.json

Conventions

  • TypeScript strict mode (tsconfig.json)
  • Style enforced by ESLint — obey the configs

Guardrails

  • Always OK: read files, run the tests (npm run test), build the project.
  • Ask first: dependency installs, deletions, migrations / schema changes.
  • Never: force-push, push to main, commit secrets, commit .env.local.

Definition of Done

Done when: npm run lint exits 0 · npm run test passes · committed with a clear message.

Security & secrets

  • Secrets live in .env.local. Never read or commit them.

Commit & PR

  • Write a clear, descriptive commit message.
  • Branch off main; never commit to main directly — open a PR for review.
  • If build/test scripts or layout change, refresh this file in the same PR (npx agents-md-facts).
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 · 60 lines · 369 tokens per session scan A 32db35cd60a3

Subscribe to this mod's changes

faf-mcp AGENTS.md is an instructions file published in the GitHub repository Wolfe-Jam/faf-mcp (6 stars, last pushed 13d ago), licensed MIT. It adds 369 tokens to every session, about $0.0018 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.

aiai-contextcursordeveloper-toolsfafmcp
Related

Other instructions, from other repositories

faf-cli AGENTS.md

Instructions for Wolfe-Jam/faf-cli, covering agents.md — faf-cli, setup & build, run the tests, where things live and conventions.

Wolfe-Jam/faf-cli · 999 tokens

faf CLAUDE.md

Instructions for Wolfe-Jam/faf, covering claude.md — @faf/specification, what this is, stack, context and 🏎️ claude.md - @faf/specification.

Wolfe-Jam/faf · 3,182 tokens

faf-cli copilot-instructions.md

Instructions for Wolfe-Jam/faf-cli, covering github copilot instructions — faf-cli v6, tech stack and project context.

Wolfe-Jam/faf-cli · 320 tokens

faf-cli CLAUDE.md

Instructions for Wolfe-Jam/faf-cli, covering claude.md — faf-cli, what this is, stack and context.

Wolfe-Jam/faf-cli · 300 tokens

faf-cli GEMINI.md

Instructions for Wolfe-Jam/faf-cli, covering gemini.md — faf-cli v6 and stack.

Wolfe-Jam/faf-cli · 177 tokens

grok-faf-mcp AGENTS.md

Instructions for Wolfe-Jam/grok-faf-mcp, covering agents.md — grok-faf-mcp, project context, stack and human context.

Wolfe-Jam/grok-faf-mcp · 566 tokens