What is gemini-faf-mcp AGENTS.md?

A project instruction file for the gemini-faf-mcp repository. It explains FAF, a registered format for storing a project’s core context, and describes the Python MCP server that reads, checks, scores, and exports it.

Use it when working on the server, its FAF validation and export behavior, its BigQuery integration, or its pytest and WJTTC test suites.

It gives AI agents the project’s purpose, technology choices, and required context so developers do not have to restate them each session.

How Wolfe-Jam/gemini-faf-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Wolfe-Jam/gemini-faf-mcp. 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/Wolfe-Jam/gemini-faf-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Wolfe-Jam/gemini-faf-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/wolfe-jam/gemini-faf-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/wolfe-jam/gemini-faf-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/wolfe-jam/gemini-faf-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wolfe-jam/gemini-faf-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/wolfe-jam/gemini-faf-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/wolfe-jam/gemini-faf-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,034 This file is loaded in full into every session.

When invoked 1,034 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.

Model	Per session	Once invoked
Fable 5.1	$0.01034	$0.01034
Opus 5.5	$0.00414	$0.00414
Sonnet 5.5	$0.00207	$0.00207
Haiku 4.5	$0.00103	$0.00103

Measured today against content hash f216f1e24f77, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gemini-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 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.

AGENTS.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — gemini-faf-mcp

MCP server for FAF — read, validate, auto-detect, score, and export IANA-registered .faf project DNA from Gemini CLI — Python · type: mcp · v3.1.2

Authored by faf — do not edit the managed block; refresh with faf export --agents. Hand-written content outside the managed block is preserved.

Setup & build

pip install -e ".[dev]"    # install
python -m build    # build

Run the tests

pytest -q
ruff check .
mypy server.py models.py safe_path.py inject.py src/

Where things live

Path	Role
`server.py`	the FastMCP server, every @mcp.tool
`models.py`	15 reference project.faf templates for faf_model
`safe_path.py`	confine_file_op, every write stays in the project root
`inject.py`	non-destructive faf-managed-block injection
`interrogate.py`	Full-Facts grounding for faf_auto (docker-compose + Makefile signals)
`src/gemini_faf_mcp/`	client.py + parser helpers over faf-python-sdk
`main.py`	Cloud Run / functions-framework entry point
`tests/`	pytest, the WJTTC 9-tier suite
`pyproject.toml`

Conventions

Quality Bar: zero_errors
Testing: required
Style enforced by ruff · mypy — obey the configs

Guardrails

All changes must pass the full test suite (pytest -q) before commit
faf-python-sdk handles parsing — server.py delegates
Version must match in pyproject.toml, init.py, client.py, server.py, main.py
Always OK: read the tree · run the tests (pytest -q) · build the project · ruff check ..
Ask first: dependency installs, deletions, migrations, schema changes, publish/release.
Never: force-push · push straight to main (branch and open a PR) · commit secrets.

Read the full file on GitHub · 101 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.

today Changed f216f1e24f77
12d ago Changed · -2 tokens per session 407554050f78
21d ago Changed 5d0c17ae1562
1mo ago Changed · +1 lines · +13 tokens per session b0f58e098650
1mo ago Changed d6a50e692103
1mo ago Changed · +5 lines · +96 tokens per session 42f1c4ba443a
1mo ago Changed 2a978137befe
1mo ago Changed · +1 lines · +22 tokens per session 2a5da9910c15
2mo ago Changed · +70 lines · +695 tokens per session 74a7aa642cd6
2mo ago First seen · 24 lines · 210 tokens per session scan A 249f79f1c516

Subscribe to this mod's changes

gemini-faf-mcp AGENTS.md is an instructions file published in the GitHub repository Wolfe-Jam/gemini-faf-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 1,034 tokens to every session, about $0.0041 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 2026-08-31.

Building agents Memory and context ai-context developer-tools faf gemini gemini-cli gemini-cli-extension

gemini-faf-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gemini-faf-mcp AGENTS.mdWolfe-Jam/gemini-faf-mcp	Instructions file	2	yesterday	MIT	A	1,034	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gemini-faf-mcp: Instructions file for Codex