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.
npx agentmods add instructions/vinta/hal-9000/claude-mdgit clone --depth 1 https://github.com/vinta/hal-9000Wrote 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/vinta/hal-9000/claude-md)<a href="https://agentmods.dev/instructions/vinta/hal-9000/claude-md"><img src="https://agentmods.dev/badge/instructions/vinta/hal-9000/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 | $0.00775 | $0.00775 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade B, and why
hal-9000 CLAUDE.md scanned grade B with 1 finding 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 4d 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.
- **Skills are the source of truth in `skills/`**: Distributed via Claude Code plugin marketplaces configured in `dotfiles/.claude/settings.json` (the `hal-9000` marketplace loads the published version from GitHub), and How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
macOS dev environment automation: dotfiles, AI agent configs, skills, and dev stacks.
Commands
Run make help to list targets and hal --help for the CLI.
Use make targets instead of running the underlying commands directly. They chain the right tools with the right flags.
Gotchas
- Dotfiles are the source of truth:
dotfiles/is the source of truth for files under~/.dotfiles/.claude/syncs to~/.claude/viahal_dotfiles.json. Always edit underdotfiles/, never under~/directly. - Skills are the source of truth in
skills/: Distributed via Claude Code plugin marketplaces configured indotfiles/.claude/settings.json(thehal-9000marketplace loads the published version from GitHub), and vianpx skills add vinta/hal-9000for other coding agents. - All skill descriptions must start with
Use when(may have a(project)prefix if it's a project-level skill). - For generated artifacts such as zsh completion, regenerate them with the repo command instead of editing them by hand (e.g.
make hal-completionafter modifyingbin/hal.py).
External Tool Documentation
Invoke the find-docs skill BEFORE writing code or config that touches the tools below, not only when asked about them. Do not answer from training data, even for familiar tools. Use WebFetch for user-provided URLs and the documentation links below.
Context7 Library IDs
Pre-resolved IDs for the find-docs skill. Pass directly to ctx7 docs, skipping the ctx7 library step:
| Tool | libraryId |
|---|---|
| ansible | /websites/ansible_projects_ansible |
| ansible-lint | /ansible/ansible-lint |
| betterleaks | /betterleaks/betterleaks |
| fnm | /schniz/fnm |
| github-actions | /websites/github_en_actions |
| homebrew | /homebrew/brew |
| oh-my-zsh | /ohmyzsh/ohmyzsh |
| ollama | /ollama/ollama |
| pre-commit | /pre-commit/pre-commit.com |
| pytest | /pytest-dev/pytest |
| ruff | /websites/astral_sh_ruff |
| ty | /websites/astral_sh_ty |
| uv | /websites/astral_sh_uv |
| zsh | /websites/zsh_sourceforge_io_doc_release |
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.
- 4d ago First seen · 57 lines · 775 tokens per session scan B 164fb04f0a42
hal-9000 CLAUDE.md is an instructions file published in the GitHub repository vinta/hal-9000 (125 stars, last pushed 6d ago), licensed MIT. It adds 775 tokens to every session, about $0.0039 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
coolify AGENTS.md
AGENTS.md instructions for coollabsio/coolify, covering agents.md, project overview, design reference, development environment and start dev environment (uses docker-compose.dev.yml).
microsandbox AGENTS.md
AGENTS.md instructions for superradcompany/microsandbox, covering agents.md, scope, project map, design principles and backward compatibility review.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
telepresence AGENTS.md
Instructions for telepresenceio/telepresence, covering agents.md, project overview, git workflow, design plans and build artifacts.
fulling AGENTS.md
Instructions for FullAgent/fulling, covering agents.md, project overview, tech stack, code conventions and current implementation context.
netdata CLAUDE.md
Claude Code instructions for netdata/netdata, a project described as: The fastest path to AI-powered full stack observability, even for lean teams.