What is tools CLAUDE.md?

A contributor guide for a repository of coding-agent skills and developer tools.

It helps install the repository’s tooling, run setup and development commands, edit skills, synchronize agent instructions, and test or lint changes across supported platforms.

It explains how to set up the repository, where skills are stored, how they are distributed, and which files are authoritative. This helps contributors change skills without editing generated copies by mistake.

tools CLAUDE.md — Instructions file for coding agents by jakkaj: A contributor guide for a repository of coding-agent skills…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/jakkaj/tools/claude-md

Clone the repo

git clone --depth 1 https://github.com/jakkaj/tools

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/jakkaj/tools/claude-md.svg)](https://agentmods.dev/instructions/jakkaj/tools/claude-md)

Your own site

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

Per session 6,119 This file is loaded in full into every session.

When invoked 6,119 The same file — it is already loaded in full.

Security scan D 2 findings. Scan, not verified.

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	$0.06119	$0.06119
Opus 5	$0.03060	$0.03060
Sonnet 5	$0.01224	$0.01224
Haiku 4.5	$0.00612	$0.00612

Measured 3d ago against content hash 8757b44028a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

tools CLAUDE.md scanned grade D 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 3d 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.

- **MCP smoke**: run `./setup.sh` in a sandbox and confirm MCP config files appear in `~/.claude.json`, `~/.codex/config.toml`, `~/.config/opencode/opencode.json`, etc.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.copilot/skills # nuke (preferred — nothing reads it anymore)

CLAUDE.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Contributor / Dev Guide

This file targets contributors and AI coding assistants working on this repository (editing skills, running dev tooling, debugging the sync flow). This is the single canonical contributor guide — AGENTS.md is a symlink to this file (the AGENTS-convention name for the same role); edit CLAUDE.md, never AGENTS.md. For the public/user-facing skill catalog, see README_AGENTS.md. For install patterns, see INSTALL.md.

Platform support & quick setup

macOS (Intel + Apple Silicon), Linux (Ubuntu/Debian/Fedora/Arch/…), Windows (via WSL or Git Bash).

git clone <repository-url> ~/github/tools
cd ~/github/tools
./setup.sh
source ~/.zshrc

./setup.sh is idempotent (safe to re-run). It installs developer tooling + MCP configs and auto-adds scripts/ to PATH. It does not install skills — those ship via npx skills (see below).

What this repo is

A skills repository, plus a dev-tooling installer. The skills are the product:

Skills source-of-truth: skills/<category>/<slug>/SKILL.md (top-level, mirrors mattpocock/skills).
Distribution: via npx skills@latest add jakkaj/tools (Vercel Labs CLI). There is no in-repo skill installer.
Dev-tooling installer (./setup.sh): installs Rust, code2prompt, FlowSpace, Claude Code CLI, Codex CLI, GitHub Copilot CLI, and configures MCP servers. Does not install skills.

Layout

/
├── skills/                     # Source-of-truth for skills (SKILL.md per skill)
│   ├── SDD/                    # the-flow (pipeline dispatch + sub-skills) + 10 utility skills
│   └── general/                # general-purpose skills (grill-me, perplexity-deep-research)
├── agents/                     # Installer infra only (legacy command sets removed — skills ship via npx)
│   ├── mcp/servers.json        # MCP server source-of-truth (read by install/agents.sh)
│   └── settings.local.json     # Shared agent settings
├── docs/
│   ├── plans/                  # Plan folders (NNN-slug/) produced by the SDD pipeline
│   └── skills-pipeline/        # Documentation for the SDD pipeline (README, getting-started, etc.)
├── install/                    # Per-tool installer scripts (rust.sh, agents.sh, ...)
├── scripts/                    # Utility scripts (sync-to-dist, check-skill-slugs, plan-ordinal, ...)
├── src/jk_tools/               # Auto-synced distribution mirror — DO NOT EDIT
├── setup.sh                    # Entry-point dev-tooling installer
├── setup_manager.py            # Python orchestrator (rich progress, runs install/*.sh)
└── pyproject.toml              # Package metadata (jk-tools-setup CLI)

Read the full file on GitHub · 243 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.

3d ago First seen · 243 lines · 6,119 tokens per session scan D 8757b44028a0

Subscribe to this mod's changes

tools CLAUDE.md is an instructions file published in the GitHub repository jakkaj/tools (5 stars, last pushed 18d ago), licensed MIT. It adds 6,119 tokens to every session, about $0.0306 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

tools CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade D, and why

Reads agent configuration directoriesmediumAgent snooping

Recursive force deletehighDestructive command

How it starts

CLAUDE.md — Contributor / Dev Guide

Platform support & quick setup

What this repo is

Layout

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

spec-kit AGENTS.md

codex AGENTS.md

langchain AGENTS.md

vscode oss-third-party-notices.instructions.md

next.js AGENTS.md