Borrowing it
Nothing to install: this file belongs to Wolfe-Jam/faf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Wolfe-Jam/faf/main/CLAUDE.mdgit clone --depth 1 https://github.com/Wolfe-Jam/fafWrote 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.
[](https://agentmods.dev/instructions/wolfe-jam/faf/claude-md)<a href="https://agentmods.dev/instructions/wolfe-jam/faf/claude-md"><img src="https://agentmods.dev/badge/instructions/wolfe-jam/faf/claude-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.
<a href="https://agentmods.dev/instructions/wolfe-jam/faf/claude-md"><img src="https://agentmods.dev/badge/instructions/wolfe-jam/faf/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01558 | $0.01558 |
| Opus 5.5 | $0.00623 | $0.00623 |
| Sonnet 5.5 | $0.00312 | $0.00312 |
| Haiku 4.5 | $0.00156 | $0.00156 |
Grade A, and why
faf CLAUDE.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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — @faf/specification
What This Is
.faf (Foundational AI-context Format) - Official format specification
Stack
- Language: JavaScript
Context
- Who: AI agents, developers, and tool implementers who read or write project.faf — anyone building an implementation that conforms to the format
- What: .faf (Foundational AI-context Format) - Official format specification
- Why: A portable AI-context standard needs one canonical, IANA-registered specification — the authoritative source for application/vnd.faf+yaml that every implementation conforms to
- Where: https://github.com/Wolfe-Jam/faf
- When: IANA-registered (application/vnd.faf+yaml, October 30 2025) — Specification 3.3.0
- How: Read SPECIFICATION.md and the JSON schemas; reference example.faf and examples/; implementations write and read project.faf files conforming to this spec
STATUS: BI-SYNC ACTIVE — 2026-06-20T01:17:45.287Z
CLAUDE.md — Wolfe-Jam/faf
What this is
The format specifications. Three IANA-registered media types live here, plus the schemas and conformance fixtures that let anyone check an implementation.
There is no executable code in this repo. It defines the formats; other repositories implement them.
| File | Defines |
|---|---|
SPECIFICATION.md |
.faf — context. application/vnd.faf+yaml |
MEMORY-FORMAT.md |
.fafm — memory. application/vnd.fafm+yaml |
AGENT-FORMAT.md |
.fafa — agents. application/vnd.fafa+yaml |
CONTEXT-INGESTION.md |
the ingestion contract |
BINARY-FORMAT.md |
a pointer only — the live FAFb wire spec is in faf-rust/crates/faf-fafb |
IMPLEMENTATIONS.md |
who implements what, and at which version |
schemas/ · conformance/ · examples/ |
the checkable parts |
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.
- 1mo ago Changed · -326 lines · -1,624 tokens per session bc7c20dd273d
- 2mo ago First seen · 464 lines · 3,182 tokens per session scan A 5c1324d3efff
faf CLAUDE.md is an instructions file published in the GitHub repository Wolfe-Jam/faf (18 stars, last pushed yesterday), licensed MIT. It adds 1,558 tokens to every session, about $0.0062 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 2026-08-30.
faf CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| faf CLAUDE.mdWolfe-Jam/faf | Instructions file | 18 | yesterday | MIT | A | 1,558 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | 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 |