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 rampstackco/claude-skills --skill launch-runbookgit clone --depth 1 https://github.com/rampstackco/claude-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/rampstackco/claude-skills/launch-runbook)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/launch-runbook"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/launch-runbook/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/rampstackco/claude-skills/launch-runbook"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/launch-runbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 206 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00127 | $0.01769 |
| Opus 5.5 | $0.00051 | $0.00708 |
| Sonnet 5.5 | $0.00025 | $0.00354 |
| Haiku 4.5 | $0.00013 | $0.00177 |
Grade A, and why
launch-runbook 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Runbook
Plan and execute the launch of a website, product, or major release. The runbook is the document everyone uses on launch day. Stack-agnostic.
This skill is for the launch event. For pre-launch QA, use qa-testing. For post-launch incident handling, use incident-response.
When to use
- Launching a new website or major redesign
- Migrating from one platform to another
- Releasing a major product or feature
- Coordinating cross-team launches
- Building a runbook for a recurring deploy
When NOT to use
- Pre-launch testing (use
qa-testing) - Post-launch incident response (use
incident-response) - After-launch retrospective (use
after-action-report)
Required inputs
- The launch scope (what's being launched)
- The launch window (date, time, duration)
- The team (roles, on-call rotation)
- The rollback criteria (when to abort)
- The communication plan (who tells whom what, when)
The framework: 4 phases
A launch has four phases. The runbook covers all four.
Phase 1: Pre-launch (T-30 days to T-1 hour)
Verify everything is ready before the launch window.
T-30 days:
- Final scope locked
- Cross-team commitments confirmed
- Pre-launch QA scheduled
- Comms plan drafted
T-7 days:
- Pre-launch QA complete
- All critical and major issues resolved
- Performance baseline measured
- Rollback procedures documented and tested
- DNS TTL lowered (if DNS change is part of launch)
T-1 day:
- Final go/no-go meeting
- Roles confirmed
- Communication channels set up
- Backup of current production state
T-1 hour:
- Team assembled in shared communication channel
- Tools and access verified
- Final smoke test on staging
Phase 2: Cutover (T-0)
The actual launch. Sequenced steps with owners and verifications.
Standard cutover steps:
- Announce start to internal team
- Enable maintenance mode (if applicable)
- Run final database migrations (if applicable)
- Deploy code to production
- Verify deploy completed without errors
- Run smoke tests on production
- DNS cutover (if applicable)
- Verify DNS propagation
- Disable maintenance mode
- Run full smoke tests on production
- Announce launch to internal team
- Begin monitoring window
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 First seen · 237 lines · 127 tokens per session scan A 8d1f7b18667d
launch-runbook is a skill published in the GitHub repository rampstackco/claude-skills (985 stars, last pushed 3d ago), licensed MIT. It adds 127 tokens to every session and 1,769 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
netlify-development
Best practices for building and deploying Netlify sites, covering serverless and edge functions, Netlify Blobs storage, the Image CDN, and build configuration. Use when writing Netlify Functions or Edge Functions, configuring netlify.toml or redirects/headers, managing environment variables across deploy contexts…
agents-v2-py
Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.
cloudflare-development
Cloudflare Workers, Pages, KV, D1, R2, and Durable Objects development best practices for edge computing applications.
gcp-development
Google Cloud Platform (GCP) development best practices for Cloud Functions, Cloud Run, Firestore, BigQuery, and Infrastructure as Code.
aws-development
AWS development best practices for Lambda, SAM, CDK, DynamoDB, IAM, and serverless architecture using Infrastructure as Code.
microservices
Guidelines for building production-grade microservices with FastAPI/Python and Go, covering serverless patterns, clean architecture, observability, and resilience.