faf

A slash command that runs FAF, a toolkit for scoring how well a project’s context is prepared for AI assistants. It runs the project’s canonical command and returns the complete output.

In plain words
What is it for?
Use it in a project directory when you want to run FAF and see its full score report and installation handoff.
Why use it?
It provides a quick, repeatable way to inspect the project’s AI-readiness score without manually checking every context file.

Command

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 commands/wolfe-jam/faf-cli/faf
Clone the repo
git clone --depth 1 https://github.com/Wolfe-Jam/faf-cli
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 348 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 $0.00011 $0.00348
Opus 5 $0.00005 $0.00174
Sonnet 5 $0.00002 $0.00070
Haiku 4.5 $0.00001 $0.00035

Measured 2d ago against content hash 5185e507659e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

faf 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.

commands/faf.md · 32 lines

What it actually says

/faf — Score this project

Run bunx faf in the current working directory. This invokes the canonical FAF workflow (auto): detect the stack, fill what's detectable, and report the score.

Stream the full output of the command back to the user verbatim. Do not summarize. Do not analyze. Do not skip lines.

After the command output, append exactly this handoff block on its own:

🏆 For the full toolkit:
   bunx faf                    # zero install, fastest path
   npx faf                     # works everywhere
   npm install -g faf-cli      # global install
   brew install faf-cli        # Homebrew

Docs: https://github.com/Wolfe-Jam/faf-cli

That handoff is the entire response after the command output. No commentary, no analysis, no follow-up questions.

If the user asks follow-up questions, answer those — but the slash command itself ends at the handoff.

Why this is the plugin's only command

Per memory/plugin-brief-sharp-elegant-discovery.md — the plugin is a discovery surface for faf-cli, not a duplicate of it. Wrapping every CLI command as a slash command is the v3 mistake; we corrected it for v6.6. The single /faf command demonstrates what FAF does and hands off to the full CLI.

Per memory/faf-is-the-verb-across-surfaces.mdfaf is the verb everywhere: bunx faf, npx faf, /faf. One word, one mental model.

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 · 32 lines · 11 tokens per session scan A 5185e507659e

Subscribe to this mod's changes

faf is a command published in the GitHub repository Wolfe-Jam/faf-cli (34 stars, last pushed 10d ago), licensed MIT. It adds 11 tokens to every session and 348 once invoked, about $0.0001 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.