What is claude-toolz CLAUDE.md?

Project instructions for the claude-toolz repository, a marketplace containing four Claude Code plugins. They describe the repository layout and its development commands.

Use them when working on plugin manifests, slash commands, skills, hooks, marketplace entries, formatting, linting, tests, or plugin validation.

They give coding agents the project context needed to make compatible changes and run the right checks.

How taylorleese/claude-toolz configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to taylorleese/claude-toolz. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/taylorleese/claude-toolz/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/taylorleese/claude-toolz

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/taylorleese/claude-toolz/claude-md.svg)](https://agentmods.dev/instructions/taylorleese/claude-toolz/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/taylorleese/claude-toolz/claude-md"><img src="https://agentmods.dev/badge/instructions/taylorleese/claude-toolz/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,321 This file is loaded in full into every session.

When invoked 1,321 The same file — it is already loaded in full.

Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01321	$0.01321
Opus 5	$0.00660	$0.00660
Sonnet 5	$0.00264	$0.00264
Haiku 4.5	$0.00132	$0.00132

Measured 8d ago against content hash 9413681eead5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-toolz CLAUDE.md scanned grade A 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- HTTP providers are mocked by patching `urllib.request.urlopen`; CLI providers by patching `shutil.which` and `subprocess.run`. Tests must never make a

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- HTTP providers are mocked by patching `urllib.request.urlopen`; CLI providers by patching `shutil.which` and `subprocess.run`. Tests must never make a

CLAUDE.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

A Claude Code plugin marketplace. Four plugins live under plugins/, each advertised in .claude-plugin/marketplace.json.

This repo is not a Python package. There is no [project] table, no lockfile, and nothing is published to a package index. The only Python is plugins/ask-llm/skills/ask-llm/scripts/ask.py (standard library only) and its tests.

Key Commands

make test - Run tests (pytest)
make lint - Run all linters via pre-commit
make format - Auto-format code
make check-plugins - Verify every plugin in marketplace.json resolves on disk
make refresh-plugins - Refresh the local marketplace mirror + installed plugins from origin/main
make all - format + lint + test

Project Structure

.claude-plugin/marketplace.json - the plugin list Claude Code reads
plugins/<name>/.claude-plugin/plugin.json - per-plugin manifest; name must match the marketplace entry
plugins/<name>/commands/ - slash commands
plugins/<name>/skills/ - skills (model-invoked)
plugins/<name>/hooks/ - hooks
scripts/check_plugins.py - validates the manifest; run by CI
tests/ - pytest tests for ask.py; all network calls are mocked

Plugins

ask-llm - /ask-llm plus a model-invoked skill. ask.py has two transports: the http provider (deepseek) POSTs to a REST endpoint with an API key, and cli providers (codex, agy) shell out to a local agent that authenticates against the user's own subscription — the script never reads or transmits a credential for those. --list prints live readiness; ASK_LLM_DISABLED_PROVIDERS hides providers the user cannot use. Keep it standard-library only; adding a dependency reintroduces the packaging and patching burden this plugin exists to avoid. CLI logins are interactive and must never be scripted — on an auth failure the script names the command and the caller relays it.
precommit-detect - SessionStart/PostToolUse hooks that detect pre-commit setup state and walk through approval-gated installs.
resolve-github-alerts - /resolve-github-alerts plus a model-invoked skill. Triages and resolves GitHub security alerts across pip/pip-tools/poetry/uv/npm/cargo/go/docker/actions ecosystems and opens a single PR for review.
revise-all-docs - /revise-all-docs captures session learnings; /improve-all-docs (and the all-docs-improver skill) run static quality audits. Depends on claude-md-management@anthropics.

Read the full file on GitHub · 83 lines

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.

8d ago First seen · 83 lines · 1,321 tokens per session scan A 9413681eead5

Subscribe to this mod's changes

claude-toolz CLAUDE.md is an instructions file published in the GitHub repository taylorleese/claude-toolz (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,321 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

claude-toolz: Instructions file for Claude Code