Borrowing it
Nothing to install: this file belongs to haoxiang-xu/PuPu. 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/haoxiang-xu/PuPu/main/.agents/skills/release-operator/SKILL.mdgit clone --depth 1 https://github.com/haoxiang-xu/PuPuWrote 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/haoxiang-xu/pupu/release-operator)<a href="https://agentmods.dev/skills/haoxiang-xu/pupu/release-operator"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/release-operator/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/haoxiang-xu/pupu/release-operator"><img src="https://agentmods.dev/badge/skills/haoxiang-xu/pupu/release-operator.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 | $0.00054 | $0.00877 |
| Opus 5 | $0.00027 | $0.00439 |
| Sonnet 5 | $0.00011 | $0.00175 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
release-operator 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 today.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PuPu Release Operator
Operate the existing release workflows through the deterministic repository CLI. This skill is an operator, not a release authority.
Authority boundary
- Read-only
plan,status, andwaitmay run without extra approval. - Immediately before every
dispatch, state the exact phase, tag, commit/run inputs, and external effect, then obtain a fresh instruction from the project owner. Never carry approval from an earlier phase. - Never approve a GitHub Environment, move or create a tag, close an issue, change Project state, decide GO, or select a fuzzy latest run.
- Stage creates or updates a Draft Release after protected approval. Publish makes that Draft public after a separate protected approval. Treat them as distinct mutations.
- If the Release still has code to land, stop before Stage even when candidate and qualification are green.
Canonical CLI
Use only:
node scripts/release-qa/release-operator.mjs <command> ...
Commands:
plan: validate an exact phase/ref/input tuple without GitHub mutation.dispatch: start one confirmed workflow and return its exact run ID/URL.status: read one exact run ID and project its jobs/artifacts/blockers.wait: resume observation of one exact run ID for a bounded period; it never retries or dispatches.
The CLI defaults waits to three hours and polls every 20 seconds. Increase the timeout only when the project owner wants continued monitoring; never shorten it merely to make a long packaging job fail sooner.
Phases
Candidate
Plan with the immutable release tag and full 40-character Unchain revision. Dispatch only after confirmation START_CANDIDATE.
node scripts/release-qa/release-operator.mjs plan --phase candidate --repo haoxiang-xu/PuPu --tag vX.Y.Z --unchain-ref <40-char-sha>
Qualification
For ordinary releases, use qualification with the exact successful candidate run ID and lower stable from-tag. For the frozen v0.1.10 baseline only, use bootstrap. Confirm with START_QUALIFICATION or START_BOOTSTRAP_QUALIFICATION respectively.
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.
- today First seen · 79 lines · 54 tokens per session scan A 23dfab7fa1b0
release-operator is a skill published in the GitHub repository haoxiang-xu/PuPu (36 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 877 once invoked, about $0.0003 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 2026-09-09.
Other skills, from other repositories
release-readiness-check
Verify all prerequisites are met before a release by checking PRs, CI/CD status, environment health, and blocking issues across GitHub, ArgoCD, and Jira. Use before cutting a release, deploying to production, or during release planning.
oma-dev-workflow
Use when setting up or optimizing developer workflows in a monorepo, managing mise tasks, git hooks, CI/CD pipelines, database migrations, or release automation. Invoke for development environment setup, build automation, testing workflows, and release coordination.
b3os-release-ops
A release and deployment checklist for the b3os project. It covers merging code, live releases, urgent fixes, and changes to public Git history.
skill-release-engineering
Prepara releases seguros com changelog, migrações, smoke tests, rollback, feature flags, CI e checklist operacional.
merge-queue-thrash-stop-inflow-and-open-prs-as-drafts
When main moves faster than the slowest CI leg, every open branch goes stale before it can merge and the whole queue jams with nothing red. Use when: (1) several PRs sit at mergeStateStatus BEHIND with auto-merge armed and none of them lands; (2) branches are being updated, re-running CI and going stale again before…
github-actions
GitHub Actions workflow generator — CI/CD pipelines, releases, Docker builds, reusable workflows, composite actions, dependabot. Use for .github/workflows/ generation, debugging, and security hardening.