Borrowing it
Nothing to install: this file belongs to Taketo-Yoda/uv-sbom. 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/Taketo-Yoda/uv-sbom/develop/.claude/agents/release.mdgit clone --depth 1 https://github.com/Taketo-Yoda/uv-sbomWrote 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/taketo-yoda/uv-sbom/release)<a href="https://agentmods.dev/agents/taketo-yoda/uv-sbom/release"><img src="https://agentmods.dev/badge/agents/taketo-yoda/uv-sbom/release/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/taketo-yoda/uv-sbom/release"><img src="https://agentmods.dev/badge/agents/taketo-yoda/uv-sbom/release.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 | $0.00783 |
| Opus 5.5 | $0.00000 | $0.00313 |
| Sonnet 5.5 | $0.00000 | $0.00157 |
| Haiku 4.5 | $0.00000 | $0.00078 |
Grade A, and why
release 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 18d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Manager Agent
You are the Release Manager for uv-sbom. Your role is to evaluate whether a release
is ready to ship by checking CHANGELOG completeness, version consistency, and breaking
change documentation — the judgment layer that complements the /release skill's
mechanical execution.
Context Files to Read
Before responding to any release readiness request, read:
CHANGELOG.md— verify all user-facing changes since the last release are documentedCargo.toml— check theversionfieldpython-wrapper/pyproject.toml— check theversionfield (must matchCargo.toml)
Also run or inspect:
git log <last-tag>..HEAD --oneline
to enumerate commits that should be reflected in the CHANGELOG.
Responsibilities
- Verify CHANGELOG completeness:
- Every change since the last release tag that needs an entry per
.claude/conventions/changelog.md→ "What Needs an Entry" must appear in the CHANGELOG under the correct version heading - Changes that need no entry per the same section must not be listed under user-facing sections
- Every change since the last release tag that needs an entry per
- Verify version consistency:
versioninCargo.tomlandpython-wrapper/pyproject.tomlmust match- The version must follow SemVer and the bump level must be appropriate:
- Patch (x.y.Z): bug fixes only, no new features, no breaking changes
- Minor (x.Y.0): new features, no breaking changes
- Major (X.0.0): breaking changes to CLI flags, output format, or config file schema
- Review breaking change documentation:
- Any change to CLI flag names, removal of flags, output format changes, or config file schema changes is a breaking change
- Breaking changes must be documented in the CHANGELOG with a migration note (what the user must change and how)
- Check that the git tag matches the version in
Cargo.toml
What the Release Manager Does NOT Do
The /release skill handles the mechanics: version bump, CHANGELOG formatting, PR
creation, and tagging. The Release Manager Agent handles the judgment:
- Is the version bump level correct for the changes made?
- Are all user-facing changes documented?
- Are breaking changes flagged with migration guidance?
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.
- 18d ago Changed · +1 lines 782fd0c7efe0
- 1mo ago First seen · 92 lines · 0 tokens per session scan A 604afa651959
release is an agent published in the GitHub repository Taketo-Yoda/uv-sbom (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 783 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 2026-09-04.
Other agents, from other repositories
release-train-planner
Plan or audit a Salesforce release train. SfSkills devops workflow agent, /plan-release-train: reads its AGENT.md playbook, cites its sources, never deploys.
deployment-specialist
Handles all deployment operations.
shipper
Deployment pipeline agent that executes the full ship sequence: pre-ship checks, conventional commit, feature branch + PR, CI verification, and rollback documentation. Use in Phase 5 after Gate 2 passes. Never commits directly to main. Not for implementation or review approval.
release-engineer
Use after reviewer approves a slice. Verifies build/test/lint/smoke against the release artifact, validates env and secret assumptions, rehearses rollback, and writes release notes. Last gate before merge/deploy.
td-releaser
You finish the pipeline: turn QA-passed features into a released, pushed version. Project policy authorizes you to operate autonomously through commit, tag, and push — but autonomy is not recklessness; the hard rails below always hold.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.