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 gtapps/claude-code-hermit --skill pre-release-reviewgit clone --depth 1 https://github.com/gtapps/claude-code-hermitWrote 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/gtapps/claude-code-hermit/pre-release-review)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/pre-release-review"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/pre-release-review/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/gtapps/claude-code-hermit/pre-release-review"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/pre-release-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 165 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00188 | $0.03159 |
| Opus 5.5 | $0.00075 | $0.01264 |
| Sonnet 5.5 | $0.00038 | $0.00632 |
| Haiku 4.5 | $0.00019 | $0.00316 |
Grade A, and why
pre-release-review 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- pre-release-review — 95% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Release Review
Run this gate immediately before $release or $fleet-release. Answer:
- What is actually shipping in each plugin?
- Does each plugin's
[Unreleased]changelog accurately describe that diff? - Per the mode picked in Step 0: does a dedicated Codex review find correctness problems in the union release window (Step 4), or is what shipped the right design for a downstream hermit (Step 3D)?
Keep Steps 1–3 and 3D read-only. Do not edit changelogs, bump versions, commit, tag, or push. Step 4 may edit only when the user chose the disclosed review-and-fix mode in Step 0.
Invocation
$pre-release-review— audit every plugin with commits since its own last tag.$pre-release-reviewfor one or more<plugin-slug>s — audit only those plugins.- Any trailing free text is the objective: it settles the Step 0 mode when it clearly names one ("design review", "run the deep pass too") and otherwise becomes the lens the verdict answers.
When installed, $release-status is an optional lightweight precursor. $docs-drift is the documentation follow-up after this changelog-vs-code audit.
Step 0 — Pick the mode
Ask once, in one message, before any git work, unless the invocation already settles it. Offer three options and accept a free-text objective alongside any of them:
- Readiness audit (default) — Steps 1–3. Cheap, read-only.
- Audit + deep correctness review — Steps 1–4. Choosing this authorizes the Step 4 native code review (read-only) and the disclosed confirmed-fix pass; state the cost and that confirmed fixes edit the working tree, and do not ask again later.
- Design review — Steps 1–3, then Step 3D: an adversarial critique of what shipped (overengineering, alternative designs, downstream-hermit impact), sourced from the PRs, issues, and proposals behind the window. Read-only.
A free-text objective does two things: the Verdict answers it ("ready to tag for ", never an unqualified ready), and Step 3 flags anything in the window that does not serve it as scope creep, even when it is correctly documented.
What ships with it
1 file 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.
- 1mo ago Changed 55b6cd186e65
- 1mo ago First seen · 220 lines · 188 tokens per session scan A 43d0f2559619
pre-release-review is a skill published in the GitHub repository gtapps/claude-code-hermit (82 stars, last pushed today), licensed MIT. It adds 188 tokens to every session and 3,159 once invoked, about $0.0008 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.
Other skills, from other repositories
release
Bump a plugin's version, write a detailed changelog entry for the upgrade skill to consume, and commit+push. Takes a plugin slug argument identifying which plugin under plugins/ to release. Use this skill whenever the user says "release", "version bump", "cut a release", "changelog and push", or finishes a set of…
fleet-release
Use this skill whenever the user wants to release, ship, prep, or cut versions for two or more plugins together on the current branch. Trigger on phrasings like "release both plugins", "ship them together", "release all changed plugins", "fleet release", "multi-plugin release", "release in order", or "release…
release-status
Use this skill to answer "what's ready to ship?", "where does the release pipeline stand?", "any plugins awaiting tag?", or "give me a pipeline overview". Shows plugin versions, tags, commits ahead, unreleased changes, and core compatibility. Read-only.
gh-cli
GitHub CLI (gh) reference for repos, issues, PRs, Actions, releases, gists, projects, codespaces, and the API.
release-management
Cut a semver release from conventional commits — bump, grouped changelog, annotated tag, GitHub release.
ccc-rollback
Roll production back by picking a known-good commit or tag, creating atomic git revert commits, pushing them, redeploying through the $ccc-deploy runners, and verifying health. Use when a deploy is bad, production is broken, or the user asks to revert or roll back a release.