Borrowing it
Nothing to install: this file belongs to gf-labs/claude-toolbox. 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/gf-labs/claude-toolbox/main/CLAUDE.mdgit clone --depth 1 https://github.com/gf-labs/claude-toolboxWrote 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/gf-labs/claude-toolbox/claude-md)<a href="https://agentmods.dev/instructions/gf-labs/claude-toolbox/claude-md"><img src="https://agentmods.dev/badge/instructions/gf-labs/claude-toolbox/claude-md.svg" alt="Measured on agentmods" 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 | $0.01367 | $0.01367 |
| Opus 5 | $0.00683 | $0.00683 |
| Sonnet 5 | $0.00273 | $0.00273 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade C, and why
claude-toolbox 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`CLAUDE_TOOLBOX_ROOT` must be set in `~/.claude/settings.json`. It points to this repo's Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
`tools` plugin (gfl-marketplace). Commands are namespaced `/tools:*`. How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
What this is
claude-toolbox — versioned personal Claude Code commands, scripts, and agents. Delivered as the
tools plugin (gfl-marketplace). Commands are namespaced /tools:*.
How scripts are called
Commands call scripts via !python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/foo.py. The env var
CLAUDE_TOOLBOX_ROOT must be set in ~/.claude/settings.json. It points to this repo's
absolute path.
The git-policy-auditor agent reads the policy path from CLAUDE_TOOLBOX_GIT_POLICY (set in
~/.claude/settings.json env); unset falls back to templates/git-policy/default-policy.md.
TaskWarrior project slug (scripts/_slug.py)
scripts/_slug.py is the single source of truth for mapping a repo path → TaskWarrior
project slug. collect-pin.py, collect-tasks.py, and the /tools:* command markdown all
go through it (the markdown invokes it as python3 ${CLAUDE_TOOLBOX_ROOT}/scripts/_slug.py).
- Default (mechanism):
slug = repo basename— no assumption about where repos live. - Opt-in (policy), via
~/.claude/settings.jsonenv:CLAUDE_TOOLBOX_REPOS_ROOT— anchor dir repos live under (also the--discoverdefault).CLAUDE_TOOLBOX_SLUG_STRATEGY—basename(default) ordomain.repo(<first-component-under-root>.<basename>, skipping any_container/in between).
This keeps the published plugin generic; a personal config (e.g. dot-configs) sets the env
to restore the ~/Repos/<domain>/<repo> → domain.repo convention. --discover walks
_name/ containers without spending a depth level and skips .name/ dormant dirs.
How to add a new command
- Create
commands/[name].mdwith standard frontmatter - If it needs a script: add
scripts/collect-[name].pyorscripts/[name].py - Bump version in
.claude-plugin/plugin.json - Changes take effect automatically on next session start (plugin loads via
--plugin-dir)
Command frontmatter fields
| Field | Required | Notes |
|---|---|---|
description |
Yes | Shown in /skills list |
allowed-tools |
Yes | e.g. Bash, Read, Write, Edit |
model |
No | Defaults to session model; use claude-haiku-4-5-20251001 for fast/cheap commands |
argument-hint |
No | Hint shown in autocomplete, e.g. [--dry-run] |
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.
- 7d ago First seen · 102 lines · 1,367 tokens per session scan C e4b9fdb4a5da
claude-toolbox CLAUDE.md is an instructions file published in the GitHub repository gf-labs/claude-toolbox (2 stars, last pushed 2d ago), licensed MIT. It adds 1,367 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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).
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.