Borrowing it
Nothing to install: this file belongs to kounetsuman/zashiki. 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/kounetsuman/zashiki/main/CLAUDE.mdgit clone --depth 1 https://github.com/kounetsuman/zashikiWrote 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/kounetsuman/zashiki/claude-md)<a href="https://agentmods.dev/instructions/kounetsuman/zashiki/claude-md"><img src="https://agentmods.dev/badge/instructions/kounetsuman/zashiki/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/kounetsuman/zashiki/claude-md"><img src="https://agentmods.dev/badge/instructions/kounetsuman/zashiki/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 | $0.01280 | $0.01280 |
| Opus 5 | $0.00640 | $0.00640 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
zashiki 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zashiki Development Conventions
Comment Conventions
The principle is "let naming and structure speak first." When you feel a comment is needed, first consider "extracting into a function whose name expresses the intent" or "expressing it in a test."
- Inline comments: As a rule, don't write them. Leave only short notes for context that can't be read from the code, such as non-obvious workarounds grounded in actual measurements.
- JSDoc: Only when there is internal behavior that naming alone can't explain, and keep it concise.
- Tags (
@param/@returns/@see, etc.): Only the minimum when needed (extra lines from tags are acceptable; types are spoken by TS, so don't mechanically annotate every argument).
Testing
- Push logic into pure functions in shared/domain and guard it with Vitest unit tests (don't cram decision logic into e2e).
- Pre-commit gate:
pnpm build && pnpm lint && pnpm test. - Keep e2e (Playwright) thin—connectivity plus critical paths only.
Documentation (Where Design, Specs, and Context Live)
There is no dedicated design-documentation directory (docs/). Consolidate into these three:
- The spec is the test code (
*.test.ts/cargo test)—this is canonical. To change behavior, update the tests first. References like "the canonical source is xxx.test.ts" point from each README / comment to the tests. - Context lives in commits / Pull Requests. Revision logs, PDCA, and "why it ended up this way" belong here (don't write context notes like "reflects ~" in the code or README).
- Design is expressed through descriptive, declarative implementation and appropriate abstraction. If a comment is still needed, use an inline comment (following the comment conventions); if it's needed across directories, use each directory's
README.md.- Don't reference retired design documents from comments (don't add new section-number pointers). Put cross-cutting "why" in the relevant directory's README, and point to the tests rather than restating the spec detail.
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 · +6 tokens per session 81be17d5632d
- 8d ago First seen · 59 lines · 1,274 tokens per session scan A 67ee75d7cdb8
zashiki CLAUDE.md is an instructions file published in the GitHub repository kounetsuman/zashiki (2 stars, last pushed 2d ago), licensed MIT. It adds 1,280 tokens to every session, about $0.0064 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
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.