Borrowing it
Nothing to install: this file belongs to azusachino/harus-skills. 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/azusachino/harus-skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/azusachino/harus-skillsWrote 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/azusachino/harus-skills/claude-md)<a href="https://agentmods.dev/instructions/azusachino/harus-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/azusachino/harus-skills/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/azusachino/harus-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/azusachino/harus-skills/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 | $0.01007 | $0.01007 |
| Opus 5 | $0.00504 | $0.00504 |
| Sonnet 5 | $0.00201 | $0.00201 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade A, and why
harus-skills 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 3d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
harus-skills
Three Markdown skills shared across agent runtimes: asobi for durable work state, revise for evidence-backed lessons, and toolbelt for terminal tool choices. Skill behavior lives in skills/<name>/SKILL.md; this file governs contributions to the repository.
Working principles
- Read the affected skill, its callers and the current repository state before editing. Current user and workspace instructions take precedence over recalled preferences and portable skill defaults.
- Keep each skill focused on its distinct job. Include guidance that changes a decision; remove repeated policy, cached inventories, and generic advice. Preserve useful recipes and concrete safety boundaries.
- Resolve routine uncertainty through repository evidence, installed CLI help, and safe checks. Continue authorized work; ask when the unresolved choice changes scope, authority, or the risk to user data.
- Reuse existing tools and targets. Define proportionate verification; distinguish structural validation from evidence that an agent follows the guidance correctly.
- Use independent subagents when useful and permitted by the current workspace. Worktrees and parallel sessions remain explicit opt-in.
- Preserve unrelated edits and partial staging. Use conventional commits without emojis, stage named files, and run
make checkbefore committing. Pushes, PRs, and other remote mutations require explicit authorization.
Skill ownership
| Skill | Source | Boundary |
|---|---|---|
asobi |
skills/asobi/SKILL.md |
Graph scope, session/task state, recall, skill selection and requested maintenance |
revise |
skills/revise/SKILL.md |
Durable lessons with evidence; session status stays with Asobi |
toolbelt |
skills/toolbelt/SKILL.md |
Tool selection and recipes; project configuration owns the actual toolchain |
Use the Asobi skill for session start and closeout. Confirm graph scope before writes: ancestor configuration can apply inside a nested repository. Capture lessons when they would change future behavior; deduplicate and retain their evidence limits.
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.
- 3d ago Changed · +2 lines · +163 tokens per session 22410cccc7d1
- 4d ago Changed · -84 lines · -865 tokens per session scan B → A 3ac04836f299
- 12d ago First seen · 131 lines · 1,709 tokens per session scan B 5ac5d4202270
harus-skills CLAUDE.md is an instructions file published in the GitHub repository azusachino/harus-skills (5 stars, last pushed yesterday), licensed MIT. It adds 1,007 tokens to every session, about $0.0050 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
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.
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).
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.
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).