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 prgit 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/pr)<a href="https://agentmods.dev/skills/vinta/hal-9000/pr"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/pr/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/pr"><img src="https://agentmods.dev/badge/skills/vinta/hal-9000/pr.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 | $0.00035 | $0.01089 |
| Opus 5 | $0.00017 | $0.00544 |
| Sonnet 5 | $0.00007 | $0.00218 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoking this skill IS the request. Your task is fully specified here. Never ask what to do.
Your first Bash call is cd "$(git rev-parse --show-toplevel)", alone, once. The working directory persists across Bash calls, so run every later command bare, exactly as written below. A cd ... && or $() prefix stops a command matching allowed-tools, and the merge then hits the permission gate.
The user invoked this skill with: "$ARGUMENTS"
Mode comes from the arguments first: create means create mode, update means update mode, merge means merge mode. With none of those three words, including an empty argument, run gh pr view --json state --jq .state 2>/dev/null and let its result decide: a non-zero exit (no PR for this branch) means create mode, OPEN means update mode, any other state means report that state and stop. Merge mode only ever comes from the argument.
PR material
Create mode and update mode run these steps where they say "gather PR material":
git log --format='%n%s' --name-only main..HEAD(fall back tomaster..HEAD). Each commit is a block: its subject, then the files it touched. A flat log next to a branch-wide diff stat lets the writer guess which commit touched which file.- The PR describes the net change of the branch. A commit whose subject starts with
Revert "and the commit it names cancel each other when both sit in the log, and a subject starting withchore: bumpdescribes no change. Remove those blocks from the log before passing it on. - Invoke the
write-like-meskill. Pass as argument: "Write a GitHub PR title and body. Output the title as the first line, a blank line, then the body, with no labels or headings around them. Title: one plain-English line, no type prefix, under 72 chars, no backticks. Body: 1-3 sentences of prose — what changed, why. No headings, no lists. In the body, wrap every file path, command, flag, and identifier in backticks, at every occurrence, likeplugins/hal-output-styles/plugin.json,~/.claude/skills,hal sync,say-no-more. Material:" followed by the log from step 2. - From
write-like-me's output, take the first line as title, the rest as body.
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.
- yesterday First seen · 69 lines · 35 tokens per session scan A 5915d0be92cf
pr is a skill published in the GitHub repository vinta/hal-9000 (129 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,089 once invoked, about $0.0002 per session on Opus 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 2026-09-10.
Other skills, from other repositories
draft-release-notes
Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
maintainer-ops
Use for vLLM Semantic Router issue intake, PR decisions, releases, and reviewed GitHub mutations performed on behalf of maintainers.
release
Prepare, verify, and publish Sutando engine releases. Use when asked to prepare a release proposal, determine a version bump, audit release documentation, validate release gates, create a release PR, tag a confirmed release, or publish GitHub release notes. Preparation is safe and non-publishing; tagging and…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
install
This skill should be used when the user asks to "install pikiclaw", "build and install", "deploy locally", "update local binary", "release", or "publish".