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.
npx agentmods add instructions/orellbuehler/kerf/claude-mdgit clone --depth 1 https://github.com/OrellBuehler/kerfWrote 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/orellbuehler/kerf/claude-md)<a href="https://agentmods.dev/instructions/orellbuehler/kerf/claude-md"><img src="https://agentmods.dev/badge/instructions/orellbuehler/kerf/claude-md.svg" alt="Measured on agentmods" 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 | $0.17349 | $0.17349 |
| Opus 5 | $0.08675 | $0.08675 |
| Sonnet 5 | $0.03470 | $0.03470 |
| Haiku 4.5 | $0.01735 | $0.01735 |
Grade A, and why
kerf 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 4d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 925 lines · 17,349 tokens per session scan A 308247b73aaa
kerf CLAUDE.md is an instructions file published in the GitHub repository OrellBuehler/kerf (4 stars, last pushed 4d ago), with no licence file. It adds 17,349 tokens to every session, about $0.0867 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 2026-08-31.
Other instructions, from other repositories
FableCut CLAUDE.md
Claude Code instructions for ronak-create/FableCut, covering fablecut — browser video editor, drivable by claude code, token-efficient editing (important for agents), where the files are, run and how claude code edits a video.
pinvou-agent AGENTS.md
AGENTS.md instructions for Pinvou/pinvou-agent, covering pinvou agent project conventions, core constraints, 0. local private memory, 1. development and pull request conventions and 2. codewhale and fork boundaries.
FableCut AGENTS.md
AGENTS.md instructions for ronak-create/FableCut, covering working with fablecut, project constraints and mcp entry point.
skills-manage CLAUDE.md
Instructions for iamzhihuix/skills-manage, covering claude.md, 开发命令, 前端（react + typescript）, rust 后端（tauri v2） and 完整应用.
SkillFlow AGENTS.md
AGENTS.md instructions for shinerio/SkillFlow, covering agents.md, directory organization rule - mandatory, documentation organization rule - mandatory, documentation sync rule - mandatory and configuration documentation sync rule - mandatory.
silent-Tiangong CLAUDE.md
Claude Code instructions for silent-rs/silent-Tiangong, covering claude.md, 项目概述, 常用开发命令, 构建 and 检查（快速验证）.