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 orlando-japan/claude-code-setting --skill release-playbookgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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/orlando-japan/claude-code-setting/release-playbook)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/release-playbook"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/release-playbook/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/orlando-japan/claude-code-setting/release-playbook"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/release-playbook.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 | $0.00023 | $0.01040 |
| Opus 5.5 | $0.00009 | $0.00416 |
| Sonnet 5.5 | $0.00005 | $0.00208 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
release-playbook 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release playbook
Every release is two bets: that the new code works, and that if it doesn't, you can get back to the old code fast. Bet the first honestly; make sure the second always wins.
The ideal release
- Staging deploy — new code lands in staging, runs against staging-like data. Smoke test passes.
- Canary deploy — a small fraction of production traffic (1%, or one pod, or one region) runs the new code. Metrics watched.
- Progressive rollout — 10%, 50%, 100% with pauses. Each step has a go/no-go check.
- Observation window — even at 100%, watch for an hour before declaring done.
- Release closed — document what shipped.
Any shortcut to this is a trade-off. Be explicit about which tradeoffs you're making.
Pre-flight checklist
- Code merged to main via a reviewed PR.
- CI green on main after the merge.
- Staging deploy complete and passed smoke tests.
- Feature flags set to safe defaults.
- Database migrations (if any) backward compatible.
- Rollback plan written and understood.
- Relevant teams notified (especially support, oncall).
- No incidents or freezes active.
The rollback rule
Rollback must be under 5 minutes, one command, and always available.
If rollback is "revert the PR and redeploy" (15 min build) → not good enough. You need a faster path:
- Blue-green deployment: flip traffic back to the previous color.
- Image rollback: redeploy the previous container image (30s on k8s).
- Feature flag off: for flag-gated features, no redeploy needed.
- DB rollback: this is the hard one. Migration design must make rollback possible — see
db-migration-safety.
Practice rollback. The first time you try it during an incident is the worst possible time.
Canary monitoring
During canary, watch:
- Error rate — compare canary pods to rest of production. Higher on canary = bad sign.
- Latency — p95 and p99 on canary vs baseline.
- Saturation — CPU, memory, GC pressure.
- Custom metrics — anything specific to what changed.
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 First seen · 98 lines · 23 tokens per session scan A 01362325b805
release-playbook is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,040 once invoked, about $0.0001 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
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
Release Checklist
Check release readiness and record a release note. Use for release and rollback requests.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
skill-release-engineering
Prepara releases seguros com changelog, migrações, smoke tests, rollback, feature flags, CI e checklist operacional.
cut-release
Cut a clean release — bump versions across all files, update changelog, create GitHub release.
cpv-setup-marketplace-auto-notification
Use when configuring a plugin to notify its marketplace after each release so Claude Code can auto-update users. Universal CI recipe for any plugin/marketplace pair. Used dynamically via cpv-the-skills-menu (TRDD-478d9687).