Borrowing it
Nothing to install: this file belongs to Malo-T/claude-toolbelt. 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/Malo-T/claude-toolbelt/main/CLAUDE.mdgit clone --depth 1 https://github.com/Malo-T/claude-toolbeltWrote 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/malo-t/claude-toolbelt/claude-md)<a href="https://agentmods.dev/instructions/malo-t/claude-toolbelt/claude-md"><img src="https://agentmods.dev/badge/instructions/malo-t/claude-toolbelt/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/malo-t/claude-toolbelt/claude-md"><img src="https://agentmods.dev/badge/instructions/malo-t/claude-toolbelt/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 | $0.00975 | $0.00975 |
| Opus 5 | $0.00487 | $0.00487 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
claude-toolbelt 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 10d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repository is
A Claude Code plugin marketplace. .claude-plugin/marketplace.json is the single marketplace,
listing every plugin under plugins/; there is no separate marketplace per plugin and none should
be added. Each plugin is independent — installable and usable on its own — but they all publish
from this one repository.
Two plugin shapes exist here:
- Skill plugins (
branch-recap,clean-context): askills/<name>/SKILL.mdplus optionalevals/. No hooks. - Hook plugins (
status-icons,status-sounds): ahooks/hooks.jsonwiring lifecycle events to scripts, no skill.
Commands
See the plugin-commands skill for validating, testing, iterating on, and releasing plugins in
this repository.
Architecture
The status-icons/status-sounds duplication is deliberate, not an oversight. Both plugins ship
their own byte-for-byte copy of hooks/watch.sh (a background poller keyed off
<config>/sessions/<pid>.json) because the two plugins install independently and must share
nothing — no common dependency, no shared package. The cost is that every fix to the watcher has to
be applied twice, which is exactly what scripts/check-watcher-parity.sh guards against: it strips
comments (prose is allowed to differ), normalises each plugin's name/env-prefix/callee script, and
diffs the result. When editing either watch.sh, port the change to the other copy or teach the
normalisation about a genuine per-plugin difference — do not let the check go red.
Why watch.sh exists at all: Claude Code's own Notification hook fires ~6 seconds after a
session actually starts waiting (a hardcoded delay in the binary), but the session state file
flips to "status":"waiting" immediately. watch.sh is a detached poller (started by
SessionStart, killed by SessionEnd) that watches that file directly and fires the real hook
(tab-title.sh or play.sh) at the moment the state changes, four times a second, well ahead of
the built-in notification. The built-in Notification hook stays wired up as a fallback for when
the watcher never started or has died; a .waiting marker file plus a pidfile is how the callee
(tab-title.sh/play.sh) tells "the watcher already handled this episode" apart from "the watcher
is absent, act on the late event yourself" — see the comments at the top of each watch.sh for the
exact handshake.
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.
- 10d ago First seen · 67 lines · 975 tokens per session scan A ab71b8a80463
claude-toolbelt CLAUDE.md is an instructions file published in the GitHub repository Malo-T/claude-toolbelt (2 stars, last pushed 20d ago), licensed MIT. It adds 975 tokens to every session, about $0.0049 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).
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.
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.