Borrowing it
Nothing to install: this file belongs to kstenerud/yoloai. 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/kstenerud/yoloai/main/CLAUDE.mdgit clone --depth 1 https://github.com/kstenerud/yoloaiWrote 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/kstenerud/yoloai/claude-md)<a href="https://agentmods.dev/instructions/kstenerud/yoloai/claude-md"><img src="https://agentmods.dev/badge/instructions/kstenerud/yoloai/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/kstenerud/yoloai/claude-md"><img src="https://agentmods.dev/badge/instructions/kstenerud/yoloai/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 | $0.00392 | $0.00392 |
| Opus 5 | $0.00196 | $0.00196 |
| Sonnet 5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
yoloai 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 9d 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
@AGENTS.md
Claude Code specifics
Everything above is the shared agent contract (AGENTS.md), imported so that Claude Code and
the agents that follow the AGENTS.md convention read the same rules. Only Claude-specific
mechanics belong in this file.
The quality gate runs itself here
.claude/settings.json registers the hooks below, all committed so any clone picks them up:
.claude/hooks/post-edit.shstamps the project when a source file is edited..claude/hooks/on-stop.shrunsmake checkat end of turn if the stamp exists. On failure it blocks completion and feeds the output back.scripts/check_citation_provenance.pyblocks on an edit that cites aresearch/*.mddoc nothing in the session ever opened (D122). It reads the transcript, so it keys off what you actually did rather than what you believe — which is the point, since a summary in context and a source you read are indistinguishable from the inside. The remedy is always the same: open the file. Scoped to research paths becauseD<n>/DF<n>citations land in every other commit and a hook that noisy gets disabled; that half stays review-caught, deliberately.
So you rarely need to run make check by hand — but it is still the gate, and a change is not
done until it passes.
Two things the hooks do not do:
post-edit.shexemptsdocs/*, so a docs-only edit never stamps andmake checknever runs on it. Docs sit outside the gate entirely.on-stop.shcapturesmake checkoutput and discards it on success, so a target that skips rather than fails reports that into a void.
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.
- 9d ago First seen · 32 lines · 392 tokens per session scan A c6b59007b5c5
yoloai CLAUDE.md is an instructions file published in the GitHub repository kstenerud/yoloai (210 stars, last pushed 18d ago), licensed MIT. It adds 392 tokens to every session, about $0.0020 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.