alunduil-chezmoi: Skill for Claude Code

.claude/skills/add-tool/SKILL.md

add-tool is a skill for Claude Code from alunduil/alunduil-chezmoi. It costs 50 tokens per session (1,202 once invoked), scanned A, original, 0BSD.

Bootstrap and README guide for adding a command-line tool to a computer setup. It decides where the tool belongs in the installation sequence and how the README should describe it.

In plain words
What is it for?
Use it when adding a package, downloaded program, npm or Cargo tool, GitHub extension, or shell installer to a chezmoi-managed bootstrap.
Why use it?
It prevents new tools from being installed in the wrong place or documented with the wrong setup instructions. It also separates tools that need a login from tools that only need to be found on the system path.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is alunduil/alunduil-chezmoi's own configuration. It tells Claude Code how to work on alunduil-chezmoi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything alunduil-chezmoi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alunduil/alunduil-chezmoi. 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/alunduil/alunduil-chezmoi/main/.claude/skills/add-tool/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/alunduil/alunduil-chezmoi

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.

agentmods badge for add-tool

README.md
[![agentmods](https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/add-tool/github.svg)](https://agentmods.dev/skills/alunduil/alunduil-chezmoi/add-tool)
Your own site
<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/add-tool"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/add-tool/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.

agentmods 80×15 button for add-tool

Your own site · 80×15
<a href="https://agentmods.dev/skills/alunduil/alunduil-chezmoi/add-tool"><img src="https://agentmods.dev/badge/skills/alunduil/alunduil-chezmoi/add-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,202 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01202
Opus 5.5 $0.00020 $0.00481
Sonnet 5.5 $0.00010 $0.00240
Haiku 4.5 $0.00005 $0.00120

Measured yesterday against content hash 49246fb0a79b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-tool 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 yesterday.

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.

.claude/skills/add-tool/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a tool to bootstrap

First check the tool belongs on the host, then make two decisions independently.

Libraries with no console script

uv tool install needs an executable, so a PyPI library takes one of two shapes:

  1. An installed tool imports it (plugins, optional backends): add it as a pinned --with extra on that tool, as beets carries pyacoustid.
  2. Otherwise, keep it off the host. The caller runs uv run --with <pkg>==<version> <script> and owns the pin. Stop here: no bootstrap change, no host-status entry.

Install a CLI front-end that wraps the library only when its command is itself wanted.

Auth axis

Does the tool need interactive auth (login, browser flow, API token) to do real work?

  • Yes (gh, claude, gcx, readwise, tailscale): add a check_login line to check_logins in dot_local/bin/executable_host-status.tmpl, testing local state the login leaves behind (a credential file, or a command that reads it without the network). Auth state is runtime, never managed by chezmoi.
  • No (zellij, lazygit, act, gh-poi): no login line.

Missing-tool report

host-status derives apt packages from .chezmoidata/packages.yaml and pinned tools from mise ls --missing, so those need no entry. A tool installed any other way (npm, cargo, uv, ghcup, an upstream installer) goes in its commands array.

Install mechanism

All passes live under .chezmoiscripts/.

Pick the canonical installer for the ecosystem:

Source Where Pattern
Debian package .chezmoidata/packages.yaml append to packages.apt
Pinned binary release dot_config/mise/config.toml mise entry below
npm package run_before_03 npm install -g, command -v
Cargo crate run_before_09 cargo install, command -v
PyPI package run_after_install-via-mise-tools mirror the beets block

Read the full file on GitHub · 123 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.

  1. yesterday Changed · +5 lines · -15 tokens per session 49246fb0a79b
  2. 2d ago Changed · -4 lines 34547286df3e
  3. 13d ago Changed · +9 lines 17167fe5b17f
  4. 24d ago Changed · +9 lines scan C → A 8d5c0578a0d4
  5. 1mo ago Changed · -1 lines scan E → C 0bd38d7e4e5e
  6. 1mo ago First seen · 105 lines · 65 tokens per session scan E 29bfb4fd16a0

Subscribe to this mod's changes

add-tool is a skill published in the GitHub repository alunduil/alunduil-chezmoi (2 stars, last pushed today), licensed 0BSD. It adds 50 tokens to every session and 1,202 once invoked, about $0.0002 per session on Opus 5.5. 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.