faf-expert

An expert guide to FAF files, a YAML-based project-context file that records information an AI assistant needs across sessions and tools. It also covers the faf-cli toolkit and syncing this context with files such as CLAUDE.md or AGENTS.md.

In plain words
What is it for?
Use it to create, edit, score, or sync .faf files and to understand the Foundational Context Layer described by the toolkit.
Why use it?
It helps keep project knowledge consistent when different AI assistants or coding sessions work on the same codebase.

Skill for Claude CodeCodex

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 skills/wolfe-jam/faf-cli/faf-expert
Any agent
npx skills add Wolfe-Jam/faf-cli --skill faf-expert
Clone the repo
git clone --depth 1 https://github.com/Wolfe-Jam/faf-cli

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,122 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00082 $0.02122
Opus 5 $0.00041 $0.01061
Sonnet 5 $0.00016 $0.00424
Haiku 4.5 $0.00008 $0.00212

Measured 2d ago against content hash 5db297dab44e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

skills/faf-expert/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FAF Expert — Persistent Project Context Specialist

What is .faf?

The .faf file is Persistent Project Context for AI — a single source of truth that survives across sessions, tools, and AI assistants.

  • IANA-registered media type: application/vnd.faf+yaml (registered Oct 30, 2025)
  • Anthropic-listed: modelcontextprotocol/servers PR #2759 — claude-faf-mcp shipped as "Persistent Project Context Server" (merged Oct 17, 2025)
  • Git-native: project.faf versions with your code; every clone gets full AI context
  • The CLI behind the FCL — the Foundational Context Layer for AI

The credo: FAF defines. MD instructs. AI codes.

When to activate this skill

  • Creating, editing, or scoring .faf files
  • Syncing .fafCLAUDE.md (or AGENTS.md, .cursorrules, GEMINI.md)
  • Diagnosing sub-Trophy scores and reaching 🏆 100%
  • Explaining the FCL, tier system, or app-type ladder
  • Connecting .faf work to the broader receipts: IANA, Anthropic PR #2759, MCP Registry

Install the CLI

bunx faf                       # Bun — zero install, fastest
npx faf                        # npm — works everywhere
npm install -g faf-cli         # global install
brew install faf-cli           # Homebrew

faf is the verb across every surface: bunx faf, npx faf, /faf (Claude Code plugin), faf (global). Bare faf is shorthand for faf auto — same behavior, fewer keystrokes.

The workflow

faf init → faf auto → faf go → 🏆 Trophy 100%
Command What it does
faf init Create a project.faf scaffold for your project
faf auto Auto-detect stack, fill what's detectable, score
faf go Guided interview to fill the remaining slots → Trophy
faf score Check current AI-readiness (0–100%)
faf sync Push .fafCLAUDE.md (and friends)
faf compile .faf.fafb binary (sealed, portable, deterministic)
faf check Validate .faf structure
faf info Version + system info

Read the full file on GitHub · 175 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.

  1. 2d ago First seen · 175 lines · 82 tokens per session scan A 5db297dab44e

Subscribe to this mod's changes

faf-expert is a skill published in the GitHub repository Wolfe-Jam/faf-cli (34 stars, last pushed 10d ago), licensed MIT. It adds 82 tokens to every session and 2,122 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

faf-expert

Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System.

Wolfe-Jam/grok-faf-mcp · 69 tokens

faf-ide

Use FAF context and IDE interop tools on this server — score, sync, platform formats; claim equals wire.

Wolfe-Jam/faf-mcp · 27 tokens

faf-context

Use FAF project context tools on this server — init, score, sync, discover; claim equals wire.

Wolfe-Jam/rust-faf-mcp · 24 tokens

wjttc-builder

PLAN and GENERATE WJTTC (Championship-Grade) test suites for any project. Analyzes the codebase, classifies components across the WJTTC five tiers (Brake · Engine · Aero · Tyre · Pit), writes a tiered test plan, and scaffolds executable test files. This is the BUILDER — it plans and generates; use wjttc-tester to…

Wolfe-Jam/faf-skills · 93 tokens

faf-expert

Master the IANA-registered .faf format (application/vnd.faf+yaml) — the typed, portable context that makes any AI understand your project. Covers scoring internals, MCP server config, bi-directional sync, and the full 21-slot model. The mechanic's manual for expert-level control. New to FAF? Start with faf-context to…

Wolfe-Jam/faf-skills · 98 tokens

faf-go

Guided interview to Gold Code (100% AI-Readiness). Use when helping users improve their .faf file through questions. Leverages Claude Code's AskUserQuestion for seamless integration. Just type /faf-go and answer questions till done.

Wolfe-Jam/faf-skills · 52 tokens