A collection of agent skills for handling recurring development and writing tasks. It includes skills for Git commits, simplifying overcomplicated work, researching best practices, finding blind spots, and editing instruction files.

Use its included skills to create commits, simplify designs, research an approach, audit settings, improve CLAUDE.md or AGENTS.md files, manage environment variables, or adjust writing style.

It provides reusable guidance for routine tasks that otherwise require repeating the same decisions and checks. The skills cover both coding workflow and technical writing.

hal-skills — Plugin for Claude Code by vinta/hal-9000

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.

Clone the repo

git clone --depth 1 https://github.com/vinta/hal-9000

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/plugins/vinta/hal-9000/skills/github.svg)](https://agentmods.dev/plugins/vinta/hal-9000/skills)

Your own site

<a href="https://agentmods.dev/plugins/vinta/hal-9000/skills"><img src="https://agentmods.dev/badge/plugins/vinta/hal-9000/skills/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/vinta/hal-9000/skills"><img src="https://agentmods.dev/badge/plugins/vinta/hal-9000/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 12 skills cost 754 tokens a session between them.

Security scan A 0 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.

Security

Grade A, and why

hal-skills 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 today.

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.

skills/.claude-plugin/plugin.json · 65 lines

What it actually says

{
  "name": "hal-skills",
  "displayName": "HAL Skills",
  "version": "2.13.0",
  "description": "Opinionated agentic skills that do the boring parts for you",
  "skills": [
    "./commit",
    "./pr",
    "./difference",
    "./fuck-over-engineering",
    "./best-practices",
    "./blindspot",
    "./simple-english",
    "./write-like-me",
    "./audit-agent-settings",
    "./refactor-agents-md",
    "./refactor-memory",
    "./refactor-skill"
  ],
  "author": {
    "name": "Vinta Chen",
    "email": "[email protected]"
  },
  "repository": "https://github.com/vinta/hal-9000",
  "homepage": "https://vinta.ws/",
  "documentationUrl": "https://github.com/vinta/hal-9000/blob/main/skills/README.md",
  "supportUrl": "https://github.com/vinta/hal-9000/issues",
  "license": "MIT",
  "icon": "./icon.png",
  "keywords": [
    "git",
    "commit",
    "stash",
    "hunk",
    "pull-request",
    "merge",
    "difference",
    "compare",
    "pros-and-cons",
    "over-engineering",
    "yagni",
    "simplify",
    "best-practices",
    "research",
    "blindspot",
    "unknowns",
    "simple-english",
    "global-english",
    "write-like-me",
    "writing-voice",
    "technical-writing",
    "claude-code",
    "audit",
    "claude-settings",
    "env-vars",
    "refactor",
    "claude-md",
    "codex",
    "agents-md",
    "auto-memory",
    "skill-md",
    "allowed-tools"
  ]
}

Contents

What it installs

The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 754 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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.

today Changed · -1 lines c7107090bff3
yesterday Changed 9a745be3daf0
3d ago Changed 263b9876e187
4d ago Changed 3333e256b337
5d ago Changed 53dad24fa1c4
7d ago Changed 6a593c4a5d62
13d ago Changed 8a275537afdf
14d ago Changed · -1 lines 49938ba11002
19d ago Changed 94b6127514cb
20d ago First seen · 67 lines scan A 6fd5ec123d82

Subscribe to this mod's changes

hal-skills is a plugin published in the GitHub repository vinta/hal-9000 (139 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.

Building agents Claude Code Productivity Python agent-skills ansible-playbooks codex macos

hal-skills

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

nx-plugin-for-aws

cctop

openmessage

apple-pim

che-ical-mcp

apple-mail-fast