clawvet: Skill for Claude Code

.claude/skills/release-check/SKILL.md

release-check is a skill for Claude Code from MohibShaikh/clawvet. It costs 48 tokens per session (762 once invoked), scanned A, original, MIT.

A release-checking tool for comparing a project’s version across npm, Git tags, GitHub Releases, ClawHub, and the Claude plugin marketplace.

In plain words
What is it for?
It is for checking releases before or after publishing and reporting hard failures or warnings that need attention.
Why use it?
It catches release information that is inconsistent between publishing channels, rather than trusting a successful publishing message.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is MohibShaikh/clawvet's own configuration. It tells Claude Code how to work on clawvet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clawvet configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/release-check.mjs.

Reuse

Borrowing it

Nothing to install: this file belongs to MohibShaikh/clawvet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MohibShaikh/clawvet/master/.claude/skills/release-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MohibShaikh/clawvet

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.

agentmods badge for release-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/mohibshaikh/clawvet/release-check/github.svg)](https://agentmods.dev/skills/mohibshaikh/clawvet/release-check)
Your own site
<a href="https://agentmods.dev/skills/mohibshaikh/clawvet/release-check"><img src="https://agentmods.dev/badge/skills/mohibshaikh/clawvet/release-check/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.

agentmods 80×15 button for release-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/mohibshaikh/clawvet/release-check"><img src="https://agentmods.dev/badge/skills/mohibshaikh/clawvet/release-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00762
Opus 5 $0.00024 $0.00381
Sonnet 5 $0.00010 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 9d ago against content hash 2f1c79a4d4c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

release-check 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 9d 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.

.claude/skills/release-check/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

release-check

clawvet ships to five places that drift independently. Verify state; never infer it from a success screen.

Run it

node scripts/release-check.mjs

Exit 0 = no hard failures. Exit 1 = at least one FAIL. Report the output as-is and fix what it flags — do not summarize a FAIL away.

What each level means

  • FAIL — a real inconsistency. Fix before claiming the release is done.
  • WARN — needs a human decision, not automatically wrong. A ClawHub version behind npm is expected (see below); a dirty tree before a release is not.
  • ok — verified against the source of truth, not assumed.

Where the releases live

Channel How it updates Automated?
npm v* tag push → .github/workflows/release.yml yes
GitHub Release same workflow, after the npm publish yes
git tag git push origin v<version> manual
Claude plugin marketplace pushing to master is the release nothing to do
ClawHub web UI only manual

Cutting a release

  1. Bump packages/cli/package.json, add a ## <version> entry to CHANGELOG.md. Update the root SKILL.md frontmatter version too — that file is what a ClawHub re-import reads.
  2. Commit, then git tag v<version> and git push origin master && git push origin v<version>. The tag push is the trigger — pushing master alone publishes nothing.
  3. Run this check and confirm npm and the GitHub Release both moved.
  4. Update ClawHub by hand if the listing matters for this release.

Known-good oddities — do not "fix" these

  • ClawHub reports a different version than npm. ClawHub auto-assigns its own version number and ignores SKILL.md frontmatter entirely. It will never track npm exactly. The check reports ClawHub's version; it never asserts equality.
  • clawvet-guard must have exactly one tracked SKILL.md, under plugins/clawvet-guard/skills/. ClawHub matches on slug, not path, so one file serves both ClawHub and the Claude marketplace. A second copy silently drifts.

Read the full file on GitHub · 67 lines

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.

  1. 9d ago First seen · 67 lines · 48 tokens per session scan A 2f1c79a4d4c0

Subscribe to this mod's changes

release-check is a skill published in the GitHub repository MohibShaikh/clawvet (11 stars, last pushed 7d ago), licensed MIT. It adds 48 tokens to every session and 762 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 2026-08-30.