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 stark-ai-de/agent-skills --skill release-managergit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/release-manager)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/release-manager"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/release-manager/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/stark-ai-de/agent-skills/release-manager"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/release-manager.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 | $0.00059 | $0.01149 |
| Opus 5.5 | $0.00024 | $0.00460 |
| Sonnet 5.5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
release-manager 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Manager
Goal
Prepare and operate a release through repository-owned hosted workflows without creating local tags or releases.
When to use
- The user asks to prepare, review, or draft a release.
- Release setup, component impact, generated version PRs, protected publication, evidence, or OpenAI handoff needs review or execution.
When not to use
- The user wants a PR review before merge; use
pr-review. - The user wants a repository-wide maintenance audit; use
repo-health-audit. - The repository has no explicit hosted release contract; first inspect its native instructions and ADRs.
Inputs
- Requested command and its exact arguments.
- Repository release configuration, manifest, component versions, hosted runs, release environment policy, and publication evidence.
Inputs to inspect
- Inspect the repository-native
release:managesurface before selecting a route. - Check accepted ADRs, current branch/SHA, release history, component versions, hosted validation, environment policy, and evidence by layer.
Process
- Select exactly one supported workflow from the finite set below.
- Verify repository identity, protected state, and the requested command's authority.
- Run the repository-owned command. Read-only commands need no mutation approval;
every hosted dispatch or approval must include
--confirm. - Report local, hosted, publication, evidence, and portal state separately.
- Stop at the next approval or manual portal boundary.
Workflow
The complete workflow set is:
status— read-only release and workflow state.setup-check— read-only App, secret, lifecycle-label, environment, branch, and workflow preflight.impact --kind patch|minor|breaking [--skill <name>]— read-only component-impact guidance.release-pr --confirm— dispatch Release Please to create or update its draft PR.publish-plan [--recovery-release-sha <sha>] --confirm— dispatch the read-only hosted publication plan; the optional full SHA selects guarded pre-publication recovery.publish [--recovery-release-sha <sha>] --confirm— dispatch protected publication and wait for environment approval.approve --run-id <id> [--recovery-release-sha <sha>] --confirm— approve the waitingreleaseenvironment deployment, repeating the exact recovery SHA when applicable.post-release --tag vX.Y.Z --confirm— dispatch tag-bound evidence on protectedmain.openai-handoff --tag vX.Y.Z— read-only handoff checklist after verifying the latest three-asset release and a newer successful exact-tag Evidence run.
What ships with it
2 files 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 · +9 lines 921988446380
- 1mo ago First seen · 122 lines · 59 tokens per session scan A 7e029f1c13df
release-manager is a skill published in the GitHub repository stark-ai-de/agent-skills (8 stars, last pushed 3d ago), licensed Apache-2.0. It adds 59 tokens to every session and 1,149 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
factory-deploy
Use when an approved PR head must reach production through a gated release — exact-head merge, staged canary rollout with threshold verdicts, and a SemVer-tagged release with notes plus a monitor handoff. Triggers on post-merge rollout work; not for continuous monitoring, review depth, or infra provisioning.
wrapup-sprint
Complete a sprint with retrospective, changelog update, release tagging, and (for ships-artifacts projects) release provenance — SBOM, SLSA, and signing. Use when sprint work is done, at the end of a sprint cycle, or before starting a new sprint.
ship-item
Ship a plan/todo item in a documentation-led repo — run the verify gate, integrate per the repo's model (fast-forward or PR), git mv todo→done with a shipped footer, advance the owning ADR(s) to Implemented, and regenerate INDEX. Use when the user says "ship this", "complete the plan item", "mark done", or "close out…
senmu-build-delivery
Plan or perform authorized releases, rollback, repository changes or non-routine Git work. Routine edits and commits covered by project rules need no reload.
release-notes
Write release notes from a git log, a list of merged PRs or rough notes about what changed — for the audience and in the format the user names (a customer changelog page, an email, an in-app "what's new", store text, a CHANGELOG.md entry). Says nothing the input doesn't, writes a vague change only as far as it was…
changelog-writer
Write a changelog entry from merged pull requests since the last release tag. Use when cutting a release or when asked what changed since a version.