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 skills add vinta/hal-9000 --skill audit-agent-settingsgit 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/skills/vinta/hal-9000/audit-agent-settings)<a href="https://agentmods.dev/skills/vinta/hal-9000/audit-agent-settings"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/audit-agent-settings/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.
<a href="https://agentmods.dev/skills/vinta/hal-9000/audit-agent-settings"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/audit-agent-settings.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00024 | $0.01075 |
| Opus 5.5 | $0.00010 | $0.00430 |
| Sonnet 5.5 | $0.00005 | $0.00215 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
audit-agent-settings 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 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.
Unrestricted tool accesslowExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Bash(python3 -m json.tool:*) Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Bash(curl -sfL https://code.claude.com/*) How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Agent Settings
Scan the platform's docs exhaustively, cross-reference them against the user's real config, deliver a ranked report, and apply what the user picks. Tie every suggestion to a named user fact — tailored, not generic.
Use AskUserQuestion in Claude Code, with multi-select for several picks. In Codex, use request_user_input for single choices; for several picks, present a numbered list and collect the selected numbers in a free-text reply. Use plain text when the named tool is unavailable.
1. Pick the targets
Use targets already specified by the user. Otherwise, offer the existing targets with this session's platform first: Claude Code settings, Codex config, or both. Read one reference per target:
- references/claude-code.md for Claude Code's docs mirrors, settings scopes, validator, dead-key probe, and gotchas.
- references/codex.md for the same on Codex.
Done when every target has its reference loaded.
2. Fetch ground truth
Curl each raw markdown mirror the reference lists into <scratchpad>. <scratchpad> is your session's scratchpad directory, or /tmp when the harness provides none. -f makes a missing page a failed command instead of a silently saved 404 body. These files are the only acceptable source for the scan; the reference's installed-CLI probes verify behavior, they do not replace the files.
Follow the reference's notes on how keys and variables are laid out in those files, and grep them for the full lists. Read the full entry of every key the user sets, since the entries carry the defaults, deprecations, and precedence the index omits.
3. Collect the user's real config
Read every config scope the reference lists, where it exists. When a dotfiles repo is the source of truth, read the repo copy and run git diff on it — uncommitted drift matters in step 6.
Read the platform's instruction files, rules, and memory the reference lists. These carry the workflow signals that make suggestions tailored: plugins, hooks, shell aliases, permission style, model choice, terminal, background-agent habits.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 66 lines · 24 tokens per session scan A ee152bed9c1b
audit-agent-settings is a skill published in the GitHub repository vinta/hal-9000 (139 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,075 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-17.
Other skills, from other repositories
frame-macos-notification
A template for realistic macOS Big Sur-style notification banners, with an app icon, title, message, and optional action button.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
geo-writing
Generates GEO/AEO-optimized articles designed to get AI engines (ChatGPT, Perplexity, Claude, Gemini) to cite your brand. Handles research, writing, and file output. Suggests listicle or head-to-head as starting formats if the user is unsure.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
vellum-skills-catalog
Discover bundled skills and search/install community skills from the skills.sh registry.