zashiki: Instructions file for Claude Code

CLAUDE.md

zashiki CLAUDE.md is an instructions file for Claude Code from kounetsuman/zashiki. It costs 1,280 tokens per session, scanned A, original, MIT.

Project-specific development rules for zashiki, including code style, testing, documentation, and issue practices.

In plain words
What is it for?
It guides component and function design, comments, Vitest unit tests, Playwright end-to-end tests, builds, linting, and documentation.
Why use it?
It gives the agent the conventions needed to make changes that fit the project and its existing tests.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is kounetsuman/zashiki's own configuration. It tells Claude Code how to work on zashiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zashiki configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/kounetsuman/zashiki/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/kounetsuman/zashiki

Made for: Claude Code.

Wrote 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.

agentmods badge for zashiki CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kounetsuman/zashiki/claude-md/github.svg)](https://agentmods.dev/instructions/kounetsuman/zashiki/claude-md)
Your own site
<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.

agentmods 80×15 button for zashiki CLAUDE.md

Your own site · 80×15
<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>
Per session 1,280 This file is loaded in full into every session.
When invoked 1,280 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 81be17d5632d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

CLAUDE.md · 59 lines

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.

Read the full file on GitHub · 59 lines

Changes

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.

  1. 3d ago Changed · +6 tokens per session 81be17d5632d
  2. 8d ago First seen · 59 lines · 1,274 tokens per session scan A 67ee75d7cdb8

Subscribe to this mod's changes

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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens