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 tranhieutt/software_development_department --skill release-checklistgit clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote 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/tranhieutt/software_development_department/release-checklist)<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/release-checklist"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/release-checklist/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/tranhieutt/software_development_department/release-checklist"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/release-checklist.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 | $0.00046 | $0.01586 |
| Opus 5 | $0.00023 | $0.00793 |
| Sonnet 5 | $0.00009 | $0.00317 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
release-checklist 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 6d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When this skill is invoked:
Explicit invocation only: This skill should only run when the user explicitly requests it with
/release-checklist. Do not auto-invoke based on context matching.
-
Read the argument for the target surface (
web,api,desktop,mobile, orall). If no surface is specified, default toall. -
Read
CLAUDE.mdfor project context, version information, and release surfaces. -
Read the current milestone from
production/milestones/to understand what features and behaviors should be included in this release. -
Scan the codebase for outstanding issues:
- Count
TODOcomments - Count
FIXMEcomments - Count
HACKcomments - Note their locations and severity
- Count
-
Check for test results in any test output directories, CI logs, or release validation notes if available.
-
Generate the release checklist:
## Release Checklist: [Version] -- [Surface]
Generated: [Date]
### Codebase Health
- TODO count: [N] ([list top 5 if many])
- FIXME count: [N] ([list all -- these are potential blockers])
- HACK count: [N] ([list all -- these need review])
### Build Verification
- [ ] Clean build succeeds for all target surfaces
- [ ] No release-blocking compiler or linter errors
- [ ] Build version number correctly set ([version])
- [ ] Release artifact is reproducible from tagged commit
- [ ] Configuration files and feature flags match release intent
- [ ] Schema migrations tested with rollback or recovery plan
- [ ] Packaging, signing, or publish steps validated where applicable
### Quality Gates
- [ ] Zero Sev1 (Critical) bugs
- [ ] Zero Sev2 (High/Major) bugs, or documented exceptions with owner approval
- [ ] All critical-path features tested and signed off by QA
- [ ] No regression from previous release
- [ ] Performance within budgets:
- [ ] Response time or startup time within target
- [ ] Memory usage within budget
- [ ] Load time or background job latency within budget
- [ ] No sustained error-rate increase during release candidate soak
- [ ] Monitoring and alerting verified for release-critical paths
### Product Complete
- [ ] All placeholder content replaced or removed
- [ ] All TODO/FIXME in user-facing flows resolved or documented
- [ ] All user-facing text proofread
- [ ] All text localization-ready (no hardcoded strings)
- [ ] Analytics / telemetry events verified
- [ ] Support and admin workflows tested
- [ ] Known limitations documented for support and customers
- Add surface-specific sections based on the argument:
For web:
### Surface Requirements: Web
- [ ] Core journeys tested on supported browsers
- [ ] Responsive layouts verified across target breakpoints
- [ ] Authentication, session expiry, and logout flows verified
- [ ] CDN, cache invalidation, and static asset delivery validated
- [ ] CSP, cookie consent, and security headers reviewed
- [ ] SEO metadata and robots/indexing settings reviewed if public-facing
For api:
### Surface Requirements: API
- [ ] OpenAPI / schema docs updated
- [ ] Backward compatibility or versioning impact assessed
- [ ] Auth, rate limiting, and idempotency tested
- [ ] Webhooks, retries, and signature verification tested if applicable
- [ ] Consumer-facing breaking changes communicated
- [ ] Database migrations validated against representative data
For desktop:
### Surface Requirements: Desktop
- [ ] Installer/package generated and verified
- [ ] Code signing and notarization complete if required
- [ ] Auto-update flow tested
- [ ] Clean install, upgrade, and uninstall scenarios verified
- [ ] File-system permissions and data directory behavior verified
- [ ] Crash recovery and relaunch behavior tested
For mobile:
### Surface Requirements: Mobile
- [ ] App store guidelines compliance verified
- [ ] All required device permissions justified and documented
- [ ] Privacy policy linked and accurate
- [ ] Background, resume, and offline behavior verified
- [ ] Push notification and deep link flows tested if applicable
- [ ] In-app purchase / subscription flows tested if applicable
- [ ] Crash-free launch tested on supported OS/device matrix
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.
- 6d ago First seen · 180 lines · 46 tokens per session scan A 6b736603c503
release-checklist is a skill published in the GitHub repository tranhieutt/software_development_department (72 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 1,586 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
multi-version-behavior-comparator
Compare behavior across multiple versions of programs or repositories. Use when you need to analyze how functionality changes between versions, identify regressions, compare outputs and exceptions, or validate upgrades. The skill compares execution behavior, test results, outputs, exceptions, and observable states…
done
End-of-session shipping gate — "prove it works, then ship it." Runs an evidence checklist (full test suite, lint/typecheck, build, and actually running the change — output quoted, never asserted), then a fresh-context two-stage review by a sub-agent that sees only the diff and the spec: spec-compliance first…
changelog
Generates and maintains changelogs following Keep a Changelog format. Use when updating release notes, finishing tasks, or tagging versions. For version bumps, see semantic-versioning.
production-build-verification
Build the standalone Forge artifact with strict routing inputs and confirm its static output exists.
semantic-versioning
Manages project versioning following Semantic Versioning (SemVer) principles. Calculates increments based on changes and synchronizes version across documentation and metadata. Use when the user asks to "bump the version", "prepare a release", or when the changelog skill calls for a release.
ship-preflight
Stage ⑤.a Ship sub — release-preflight gate. Runs harnessed release-preflight (read-only: CHANGELOG [Unreleased] non-empty + version + git-clean + tag-absent). A failing gate blocks shipping. Nothing is pushed/published/tagged here.