Borrowing it
Nothing to install: this file belongs to Meirtz/Shinken. 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/Meirtz/Shinken/main/CLAUDE.mdgit clone --depth 1 https://github.com/Meirtz/ShinkenWrote 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/meirtz/shinken/claude-md)<a href="https://agentmods.dev/instructions/meirtz/shinken/claude-md"><img src="https://agentmods.dev/badge/instructions/meirtz/shinken/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/meirtz/shinken/claude-md"><img src="https://agentmods.dev/badge/instructions/meirtz/shinken/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 | $0.04369 | $0.04369 |
| Opus 5 | $0.02184 | $0.02184 |
| Sonnet 5 | $0.00874 | $0.00874 |
| Haiku 4.5 | $0.00437 | $0.00437 |
Grade A, and why
Shinken 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — guide for AI coding sessions in this repo
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Shinken is an AI-native, cross-platform sandbox runtime + control plane + control panel for
computer-use agents — the runtime that benchmarks and harnesses plug into. See README.md and
docs/. The implementation has two distinct maturity axes. The
cross-platform operation-layer backend waist is built: cua, mcp-computer,
browser-runtime, and e2b expose computer-use and browser surfaces behind the same typed ACI,
and RoutedSession composes CU↔BU. Proof depth varies by external driver. Shinken's own
first-party native runtime is deepest on Linux/X11 under live CI — handshake/auth,
pointer+keyboard actions, pixel observation (screenshot + real-time screencast + bandwidth levers
and focused-window capture), Docker disk-tier checkpoint/fork/resume + the privileged-only
CRIU memory tier (live process+memory forks) + run_eval_forked, a local
capability-gateway shim, and the guest structured-observation engine v1 (Linux/AT-SPI:
observe with stable element ids, tree-text diff, settle; guest-side element_ref actions +
invoke_action/set_value). A macOS engine v1 also exists (native CoreGraphics/CGEvent
backend in shinkend; capture+input built, local-only proof — no mac CI, AX designed-only;
docs/engineering/macos-engine.md). Production permission
enforcement, .skn recording/playback, the control plane, and Shinken-owned native Windows,
Wayland, and full macOS AX engines are designed-only and not yet built. The a11y-coverage spike (#2)
has been measured (E5) — verdict: hybrid per-window structured + pixel fallback, so D3's
structured-default stays Provisional (canvas is a measured zero with a change-blind diff,
Electron is measured on both CDP and forced AT-SPI; games/native-GL still unmeasured; the
in-guest CDP backend and UIA/AX tiers remain unbuilt).
docs/engineering/status.md is the authoritative built-vs-designed map — read it before
trusting present-tense claims in the vision docs. This file's status summary must track
status.md; reconcile both when either 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.
- 9d ago First seen · 213 lines · 4,369 tokens per session scan A 64e0db1ba31f
Shinken CLAUDE.md is an instructions file published in the GitHub repository Meirtz/Shinken (21 stars, last pushed 5d ago), licensed Apache-2.0. It adds 4,369 tokens to every session, about $0.0218 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.