Borrowing it
Nothing to install: this file belongs to thejdubb02/clique. 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/thejdubb02/clique/main/.claude/skills/clique-release-check/SKILL.mdgit clone --depth 1 https://github.com/thejdubb02/cliqueWrote 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/thejdubb02/clique/clique-release-check)<a href="https://agentmods.dev/skills/thejdubb02/clique/clique-release-check"><img src="https://agentmods.dev/badge/skills/thejdubb02/clique/clique-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.
<a href="https://agentmods.dev/skills/thejdubb02/clique/clique-release-check"><img src="https://agentmods.dev/badge/skills/thejdubb02/clique/clique-release-check.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 | $0.00000 | $0.00509 |
| Opus 5.5 | $0.00000 | $0.00204 |
| Sonnet 5.5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
clique-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 13d 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.
What it actually says
Look, release, verify
Looking at it
Every other check here reasons about the code, and none of them can see that a control is invisible, that one thing is covering another, or that a theme did not reach the pane. That is where the bugs have actually been: a preview popup layered above the context menu broke right-click on every sidebar row and the suite stayed green through it.
~/.cache/clique-visual/bin/python tools/visual_check.py # asserts, and writes screenshots
Run it after any change to web/. Setup is in the file's docstring — it
needs Chromium and Playwright, so it lives in a virtualenv of its own and the
product stays standard-library with no build step. Screenshots land in
/tmp/clique-visual/; open them, do not just read the passes.
Releasing
Bump __version__, write the CHANGELOG.md entry, then run
python3 tools/stamp_changelog.py — it puts the wall-clock Pacific time on any
heading that lacks one, taking it from the release commit where there is one.
Skipping it leaves an entry the app renders without a time, and on a day with
ten releases the date alone distinguishes nothing. It is idempotent; run it
whenever.
Before calling a session done
python3 tools/shipped_check.py
Four surfaces have to agree: the panel's version, the README badge, what useclique.dev tells people to install, and what PyPI actually serves. They drift apart quietly and each one embarrasses differently, and none of it is visible from inside the panel. Ten seconds, so it is a command rather than a habit.
Being ahead of PyPI is normal while work is in flight and stops being normal
the moment the site tells a stranger to pip install, which it does. Cutting
the release is: bump, changelog, tag vX.Y.Z, gh release create. Publishing
fires on the release, uses Trusted Publishing, and needs no token.
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.
- 13d ago First seen · 50 lines · 0 tokens per session scan A 56cd8a11d782
clique-release-check is a skill published in the GitHub repository thejdubb02/clique (2 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 509 tokens. 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 2026-10-12.
Other skills, from other repositories
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
baguette
Drive and inspect iOS simulators with the baguette CLI: taps, swipes, buttons, typing, screenshots, the accessibility tree, logs, and the conditions an app runs under (location, network, appearance, push, UserDefaults), without opening Xcode. Use when an agent must act on or verify a running simulator — a UI flow…
verify-and-ship
Choose proportionate validation, fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
agent-browser
Use the host-side agent-browser CLI for local browser smoke tests, screenshots, snapshots, and simple UI validation against forwarded localhost URLs.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.