A guide for using .faf files, YAML documents that store a project's background and working rules for AI tools across sessions. It also covers related CLAUDE.md files, command-line commands, and setup.

Use it to create or update project context files, run faf-cli commands, configure the related MCP server, and assess a project's AI-readiness score.

It keeps important project context available instead of requiring you to explain it again in every AI session. It also helps keep the machine-readable .faf file and human-readable CLAUDE.md file aligned.

faf-expert — Skill for Claude Code and Codex by Wolfe-Jam

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.

Any agent

npx skills add Wolfe-Jam/grok-faf-mcp --skill skill

Clone the repo

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

Made for: Claude Code, Codex.

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/skills/wolfe-jam/grok-faf-mcp/skill/github.svg)](https://agentmods.dev/skills/wolfe-jam/grok-faf-mcp/skill)

Your own site

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

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,832 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 41
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Agent Snooping · line 365
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

How audits are shown

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	$0.00069	$0.02832
Opus 5	$0.00034	$0.01416
Sonnet 5	$0.00014	$0.00566
Haiku 4.5	$0.00007	$0.00283

Measured 9d ago against content hash 751c1cf3e88f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

faf-expert 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

faf-expert — 98% identical, 2 lines differ

skill/SKILL.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FAF Expert - Project DNA Specialist

What is .faf?

.faf is the universal format for persistent AI project context - "Project DNA ✨ for ANY AI".

Core Concepts:

Foundational AI-context Format - YAML-based project context file
Persistent Context - Survives across sessions, tools, and AI assistants
Universal - Works with Claude, ChatGPT, Gemini, Cursor, any AI
Measurable - Championship scoring system (0-100% AI-readiness)
Official Anthropic MCP Steward - PR #2759 MERGED

When to Use This Skill

Activate this skill when:

Creating or updating .faf files
Working with CLAUDE.md files
Running faf CLI commands (init, auto, score, formats, bi-sync)
Scoring project AI-readiness
Setting up MCP server (claude-faf-mcp)
Configuring tool visibility (v2.8.0+)
Discussing project context or documentation

Key Files

.faf - YAML format, machine-readable project context
CLAUDE.md - Markdown format, human-readable project guide
Bi-Sync - .faf ↔ CLAUDE.md kept in sync automatically
project.faf - v1.2.0 standard naming

Common Commands

faf-cli Commands

faf init              # Create .faf from project
faf auto              # Auto-detect stack and create .faf
faf score             # Rate AI-readiness (0-100%)
faf formats           # List 153+ supported formats
faf bi-sync           # Sync .faf ↔ CLAUDE.md
faf status            # Check project AI-readiness
faf validate          # Validate .faf structure
faf doctor            # Diagnose and fix issues
faf migrate           # Migrate to latest format

MCP Tools (claude-faf-mcp v2.8.0+)

v2.8.0 introduces Tool Visibility System:

21 Core Tools (default) - Essential workflow
51 Total Tools (opt-in) - All features

Configuration:

{
  "mcpServers": {
    "faf": {
      "command": "npx",
      "args": ["-y", "[email protected]"],
      "env": {
        "FAF_MCP_SHOW_ADVANCED": "false"
      }
    }
  }
}

Read the full file on GitHub · 386 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.

9d ago First seen · 386 lines · 69 tokens per session scan A 751c1cf3e88f

Subscribe to this mod's changes

faf-expert is a skill published in the GitHub repository Wolfe-Jam/grok-faf-mcp (18 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 2,832 once invoked, about $0.0003 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.

LLM Memory and context ai-context ai-tools faf grok mcp

kayba-ace

This skill ships learnfromtraces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.

kayba-ai/agentic-context-engine · 0 tokens

knowledge-base

Retrieves and updates project-specific prompt knowledge from comparison evidence and user feedback. Use only for prompt analysis or post-comparison learning within a Rashomon evaluation.

shinpr/rashomon · 34 tokens

hmem-write

Hmem write protocol — picks prefix (L/E/D/P/N/R/I/H…), tree location, and tags, and detects duplicates before persisting. Use before any writememory or appendmemory call (skipping it creates duplicates and misplaced entries), or when the user says 'remember this', 'save this', 'log this', or invokes /hmem-write.

Bumblebiber/hmem · 77 tokens

hmem-read

Load long-term memory from hmem via readmemory or loadproject. Use when starting fresh with no L1 summaries, after /compact, when the user asks 'what do you remember', 'continue where we left off', 'was war der letzte Stand', or about a project/topic visible in L1 summaries. Covers search, prefix filter, findrelated…

Bumblebiber/hmem · 85 tokens

hmem-config

View and change hmem memory settings, hooks, sync, and checkpoints. Use on /hmem-config, or when the user asks why context is huge, how to change auto-save, how often checkpoints fire, or how to set up sync.

Bumblebiber/hmem · 54 tokens

hmem-curate

Curate an .hmem file (your own or foreign) — mark obsolete/irrelevant, fix titles, consolidate duplicates, repair broken links. Requires the hmem-curate MCP server (skill prompts the user to enable it on entry). Use whenever the user says 'aufräumen', 'memory aufräumen', 'Speicher aufräumen', 'hmem aufräumen', 'clean…

Bumblebiber/hmem · 218 tokens