Borrowing it
Nothing to install: this file belongs to multiplex-ai/muggle-ai-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/multiplex-ai/muggle-ai-works/master/.claude/skills/muggle-works-npm-release/SKILL.mdgit clone --depth 1 https://github.com/multiplex-ai/muggle-ai-worksWrote 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/multiplex-ai/muggle-ai-works/muggle-works-npm-release)<a href="https://agentmods.dev/skills/multiplex-ai/muggle-ai-works/muggle-works-npm-release"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-works/muggle-works-npm-release/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/multiplex-ai/muggle-ai-works/muggle-works-npm-release"><img src="https://agentmods.dev/badge/skills/multiplex-ai/muggle-ai-works/muggle-works-npm-release.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 | $0.00083 | $0.03114 |
| Opus 5.5 | $0.00033 | $0.01246 |
| Sonnet 5.5 | $0.00017 | $0.00623 |
| Haiku 4.5 | $0.00008 | $0.00311 |
Grade A, and why
muggle-works-npm-release 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 3d 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.
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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Muggle Test Works — npm release (single playbook)
Maintainer-only. Lives at
.claude/skills/(mirrored to.cursor/skills/), not in the published plugin (plugin/skills/). Invokable as/mreleasewhile working in this repo; runpnpm run link:maintainer-skillsto invoke it from any project.
Repo: multiplex-ai/muggle-ai-works. Workflow: .github/workflows/publish-works-to-npm.yml (“Publish Works to npm”). Never run local npm publish (OIDC trusted publishing in CI).
Phase 1 — Ask bump type (do this first)
Stop until the user answers.
Prefer AskUserQuestion with exactly these three options: major, minor, patch (fix). If the environment has no structured question tool, ask the same in plain text:
Is this release a major, minor, or patch (fix)?
You may recommend a bump from commit subjects (e.g. feat! / breaking → major, feat → minor, fix / chore → patch) but do not choose for them. Do not edit files yet.
Phase 2 — Sync, surface state, empty-release gate
Run from muggle-ai-works:
git checkout master && git pull --ff-only && git fetch --tags
Show what is shipping:
node -e 'console.log("master package.json:", require("./package.json").version)'
npm view @muggleai/works version 2>&1 | sed 's/^/npm latest: /'
Commits since the last release commit (stop if there is nothing to ship):
LAST_RELEASE_SHA=$(git log --grep='chore(release)' --format='%H' -1)
NON_SHIPPING=(':(exclude)internal/' ':(exclude)docs/' ':(exclude)ops/' ':(exclude)test/' ':(exclude).github/' ':(exclude).claude/' ':(exclude).cursor/' ':(exclude)README.md' ':(exclude)eslint.config.js' ':(exclude)vitest.config.ts')
git log --oneline "$LAST_RELEASE_SHA..HEAD"
git diff --name-only "$LAST_RELEASE_SHA..HEAD" -- . "${NON_SHIPPING[@]}"
The log is for reading; the diff decides. NON_SHIPPING drops paths that cannot reach the npm tarball — the shipping surface is package.json → files, plus the sources dist/ is built from (src/, packages/, tsup.config.ts) and the lockfile pinning what gets bundled. The gate is a diff rather than a pathspec'd git log because path filtering makes git log simplify merge commits out of the range, which a tree-to-tree diff cannot do.
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.
- 3d ago Changed · -2 lines 7bc3034ae813
- 19d ago Changed 430df6120473
- 2mo ago Changed · +21 lines 70f9dc458122
- 2mo ago First seen · 207 lines · 83 tokens per session scan A 0ab2e6807539
muggle-works-npm-release is a skill published in the GitHub repository multiplex-ai/muggle-ai-works (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 83 tokens to every session and 3,114 once invoked, about $0.0003 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 2026-08-30.
muggle-works-npm-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| muggle-works-npm-releasemultiplex-ai/muggle-ai-works | Skill | 16 | 2d ago | Apache-2.0 | A | 83 | Claude Code |
| githubAtomicBot-ai/atomic-agent | Skill | 3.4k | 2d ago | MIT | A | 48 | Claude Code, Codex |
| AI Release GuardianPramodDutta/qaskills | Skill | 245 | 6d ago | MIT | A | 54 | Claude Code, Codex |
| release-readinesspetrkindlmann/qa-skills | Skill | 254 | 18d ago | MIT | A | 160 | Claude Code, Codex |
| upgradeai-ecoverse/slicc | Skill | 37 | today | Apache-2.0 | A | 132 | Claude Code |
| versioning-by-impactrexleimo/aios | Skill | 62 | yesterday | MIT | A | 29 | Claude Code, Codex |
| releasexonika9/agent-skills | Skill | 4 | 13d ago | MIT | A | 69 | Claude Code |