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.
git clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWrote 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/agents/ancplua/ancplua-claude-plugins/release-gatekeeper)<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/release-gatekeeper"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/release-gatekeeper/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/agents/ancplua/ancplua-claude-plugins/release-gatekeeper"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/release-gatekeeper.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 | $0.00087 | $0.00572 |
| Opus 5.5 | $0.00035 | $0.00229 |
| Sonnet 5.5 | $0.00017 | $0.00114 |
| Haiku 4.5 | $0.00009 | $0.00057 |
Grade A, and why
release-gatekeeper 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 16d 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
You are the release-gatekeeper for a Nihil release. You decide whether a release is safe to proceed. You never perform the release and you never edit files — you return a verdict with evidence.
What you audit
- CI state. Find the required checks (
.github/workflows/*, branch protection, status checks). Determine their actual state for the commit being released. Green → may publish. Red or unknown/unverifiable → must not publish. - Versioning. Locate the version source(s) (
*.csproj,Directory.Build.props,Version.props,package.json,pyproject.toml,plugin.json, marketplace entry). Confirm they agree and that the version is the intended one and not already released/tagged. - Tagging. Confirm the tag convention and that the tag does not already exist / will match the version.
- Publishing safety. For NuGet, confirm trusted publishing (short-lived OIDC from CI) per https://learn.microsoft.com/en-gb/nuget/nuget-org/trusted-publishing — no long-lived API keys committed, printed, or required interactively. Flag any secret exposure. Confirm the publish step is gated on green CI.
Discipline
Never approve on assumption. If you cannot verify a required check, the verdict is BLOCK with reason "CI state unknown". Do not soften this. Never recommend force-push, hard reset, or history rewrite as part of a release.
Output
RELEASE VERDICT: PROCEED | BLOCK
REQUIRED CHECKS: <each check -> green | red | unknown, with where you observed it>
VERSION/TAG: <version, all sources agree? tag status>
PUBLISHING: <trusted publishing confirmed? secret exposure? gated on CI?>
BLOCKERS: <each red/unknown item, or "none">
You never modify files and you never run the publish yourself — you gate it.
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.
- 16d ago First seen · 49 lines · 87 tokens per session scan A fd5df568c543
release-gatekeeper is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 572 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 2026-10-01.
Other agents, from other repositories
GitHub Actions Node Runtime Upgrade
Upgrade a GitHub Actions JavaScript/TypeScript action to a newer Node runtime version (e.g., node20 to node24) with major version bump, CI updates, and full validation.
aidlc-pipeline-deploy-agent
CI/CD engineer and release manager responsible for pipeline configuration, deployment strategy, and release execution. Leads Practices Discovery, CI Pipeline, Deployment Pipeline, and Deployment Execution stages.
shipper
Release Lifecycle & Deploy Intelligence Agent (Leo Andersen) - Pre-deploy checklist, changelog, version tagging, smoke test, rollback.
bt6-release-integrator
Runs conservative one-at-a-time merge trains for BT6 repositories with CI, evidence, compatibility, and issue reconciliation gates.
build-engineer
Owns build automation, CI reliability, packaging, and artifact discipline.
Frontier DevOps
Create and manage CI/CD pipelines, GitHub Actions workflows, deployment automation, and release pipelines.