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/saiday/kukuroo/claude-mdgit clone --depth 1 https://github.com/saiday/kukurooWrote 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/saiday/kukuroo/claude-md)<a href="https://agentmods.dev/instructions/saiday/kukuroo/claude-md"><img src="https://agentmods.dev/badge/instructions/saiday/kukuroo/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 5.1 | $0.00131 | $0.00131 |
| Opus 5 | $0.00066 | $0.00066 |
| Sonnet 5 | $0.00026 | $0.00026 |
| Haiku 4.5 | $0.00013 | $0.00013 |
Grade A, and why
kukuroo 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 6d 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.
What it actually says
Pull Requests
- Write PR titles, summaries, and descriptions in English.
Releasing
RELEASING.md is the procedure, and it is not optional reading before a publish. Two
things it is easy to get wrong from the outside:
- A publish credential never goes in
~/.npmrcor anywhere in the repo.tools/npm-token.shis the only path to one, andtools/is outsidefilesinpackage.jsonso it does not ship. - The git tag names the commit the tarball was built from, which is not always
main.
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.
- 6d ago First seen · 14 lines · 131 tokens per session scan A 08c97c921e5d
kukuroo CLAUDE.md is an instructions file published in the GitHub repository saiday/kukuroo (123 stars, last pushed 21d ago), licensed MIT. It adds 131 tokens to every session, about $0.0007 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.
Other instructions, from other repositories
ios-mcp AGENTS.md
AGENTS.md instructions for witchan/ios-mcp, covering agents.md, 一、agents.md 使用规则, 1. 文件命名规则, 2. 多个 agents.md 的处理方式 and 3. 推荐组织方式.
edgeever AGENTS.md
AGENTS.md instructions for tianma-if/edgeever, covering agents.md, 文档与分支约束, 变更风险评估, github actions 与 release 约束及流程 and 🇨🇳 中文说明 / chinese changelog.
iOS-vibebuddy AGENTS.md
AGENTS.md instructions for semantic-craft/iOS-vibebuddy, covering agents.md, verification strategy, agent skills, issue tracker and triage labels.
roamcode AGENTS.md
AGENTS.md instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.
Heeler CLAUDE.md
Claude Code instructions for ZingerLittleBee/Heeler, covering heeler, architecture, load-bearing herdr facts, conventions and agent skills.
Heeler AGENTS.md
AGENTS.md instructions for ZingerLittleBee/Heeler, a project described as: Native iOS agent console for herdr — watch and drive the coding agents on your machines over SSH, with a real libghostty terminal, QR pairing, and push notifications when an agent needs you.