Borrowing it
Nothing to install: this file belongs to hiro-o918/rinkaku. 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/hiro-o918/rinkaku/main/CLAUDE.mdgit clone --depth 1 https://github.com/hiro-o918/rinkakuWrote 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/hiro-o918/rinkaku/claude-md)<a href="https://agentmods.dev/instructions/hiro-o918/rinkaku/claude-md"><img src="https://agentmods.dev/badge/instructions/hiro-o918/rinkaku/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/hiro-o918/rinkaku/claude-md"><img src="https://agentmods.dev/badge/instructions/hiro-o918/rinkaku/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 | $0.02498 | $0.02498 |
| Opus 5 | $0.01249 | $0.01249 |
| Sonnet 5 | $0.00500 | $0.00500 |
| Haiku 4.5 | $0.00250 | $0.00250 |
Grade A, and why
rinkaku 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.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project-specific instructions for working on rinkaku.
Project overview
rinkaku (輪郭, "outline") is a CLI that condenses large PR diffs — especially LLM-generated ones — into just the signatures of changed symbols and their dependencies, so reviewers and LLMs can grasp the API surface of a change without reading every implementation line.
- Input: a unified diff via stdin (
gh pr diff 123 | rinkaku), orrinkaku --base main(runsgit diffinternally). - Core: tree-sitter parses changed files, finds the definitions containing changed lines, and slices out their signatures.
- Dependency expansion: 1-hop references via tree-sitter tags queries
(v1). LSP-based resolvers (pyright, gopls, etc.) are pluggable later
via a
Resolvertrait. - Built-in languages: Rust, Go, Python, TypeScript, and HCL (Terraform), each implemented
as a
LanguageSupporttrait impl (grammar crate + tags query + signature-slicing rule), making language support additive. - Output: Markdown or JSON, designed to be fed to LLMs.
Design rationale for the choices above is recorded in
docs/adr/.
Architecture principles
- Flat module structure: start simple, split into submodules only when a group of files sharing a responsibility grows large enough to warrant it. Do not pre-create deep module hierarchies.
- Core logic is pure: no IO, no wall clock, no environment variable
reads inside
rinkaku-core's domain logic. Diff input, file reads, process invocations (git, future LSP servers) belong at the boundary (main.rsand future adapter modules), passed in as arguments or via ports. - Ports as traits, defined on the consumer side:
LanguageSupport(tree-sitter grammar + tags query + signature slicing per language) andResolver(dependency resolution strategy) are traits defined where they are consumed, not where they are implemented. Keep them small (1-3 methods). - Composition root in
main.rs: dependency wiring (whichLanguageSupportimpls are registered, whichResolveris used) is assembled by hand inmain.rs. No DI framework, no global state, noinit()-time wiring. - Do not introduce a shared/common abstraction (e.g. a generic repository layer over language support or resolvers) speculatively — only after a concrete second use case demands it, and after discussing it in an ADR.
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 · 200 lines · 2,498 tokens per session scan A 1b7f83409932
rinkaku CLAUDE.md is an instructions file published in the GitHub repository hiro-o918/rinkaku (50 stars, last pushed 7d ago), licensed MIT. It adds 2,498 tokens to every session, about $0.0125 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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.