Borrowing it
Nothing to install: this file belongs to yangyue1974/kobox. 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/yangyue1974/kobox/main/CLAUDE.mdgit clone --depth 1 https://github.com/yangyue1974/koboxWrote 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/yangyue1974/kobox/claude-md)<a href="https://agentmods.dev/instructions/yangyue1974/kobox/claude-md"><img src="https://agentmods.dev/badge/instructions/yangyue1974/kobox/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/yangyue1974/kobox/claude-md"><img src="https://agentmods.dev/badge/instructions/yangyue1974/kobox/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 | $0.00483 | $0.00483 |
| Opus 5 | $0.00242 | $0.00242 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade C, and why
kobox CLAUDE.md scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
If `uv` is not installed, install it first: `curl -LsSf https://astral.sh/uv/install.sh | sh` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If `uv` is not installed, install it first: `curl -LsSf https://astral.sh/uv/install.sh | sh` What it actually says
Installing kobox (instructions for Claude Code)
You are installing kobox, an MCP server that controls a Teenage Engineering
EP-133 K.O. II over MIDI. Follow these steps exactly. Do not skip verification.
Steps
-
Ensure you are in the cloned
koboxrepo directory. If the user only gave you a GitHub URL, clone it first into a sensible location andcdinto it. -
Create an isolated environment and install pinned dependencies:
uv venv .venv uv pip install --python .venv/bin/python -e .If
uvis not installed, install it first:curl -LsSf https://astral.sh/uv/install.sh | sh -
Register the server with Claude Code at user scope (available in all projects). Use the ABSOLUTE path to the venv's console script:
claude mcp add kobox --scope user -- "$(pwd)/.venv/bin/kobox" -
Verify the server connects:
claude mcp get koboxExpected:
Status: ✓ Connected. -
Verify MIDI works and the device is visible (device must be plugged in via USB):
.venv/bin/python -c "import mido; print('outputs:', mido.get_output_names())"Expected: a list including
EP-133. If the list is empty or lacks EP-133, tell the user to connect the K.O. II via USB and power it on, then re-run this step. -
Tell the user to RESTART Claude Code so the
koboxtools load, then they can say "connect to my K.O. II" to begin.
Troubleshooting
No module named 'rtmidi'/ no sound: dependencies didn't install; re-run step 2.EP-133 not found: device not plugged in / powered on, or another app holds the MIDI port. Close other MIDI apps and re-run step 5.claude: command not found: the user is not in Claude Code. See README for the Claude Desktop path.
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.
- 8d ago First seen · 47 lines · 483 tokens per session scan C ac915c4eddda
kobox CLAUDE.md is an instructions file published in the GitHub repository yangyue1974/kobox (3 stars, last pushed 2mo ago), licensed MIT. It adds 483 tokens to every session, about $0.0024 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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.
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.