launch-checklist

launch-checklist is a skill for Claude Code, Codex from aakashg/pm-claude-code-setup. It costs 0 tokens per session (619 once invoked), scanned A, original, MIT.

A risk-scaled checklist for preparing, launching, and reviewing a software change.

In plain words
What is it for?
Use it for launch preparation, launch-day monitoring, and follow-up reviews for low-, medium-, or high-risk changes.
Why use it?
It helps teams check testing, rollback, monitoring, support, communication, and post-launch results before shipping.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/aakashg/pm-claude-code-setup/launch-checklist
Any agent
npx skills add aakashg/pm-claude-code-setup --skill launch-checklist
Clone the repo
git clone --depth 1 https://github.com/aakashg/pm-claude-code-setup

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for launch-checklist

README.md
[![agentmods](https://agentmods.dev/badge/skills/aakashg/pm-claude-code-setup/launch-checklist.svg)](https://agentmods.dev/skills/aakashg/pm-claude-code-setup/launch-checklist)
Your own site
<a href="https://agentmods.dev/skills/aakashg/pm-claude-code-setup/launch-checklist"><img src="https://agentmods.dev/badge/skills/aakashg/pm-claude-code-setup/launch-checklist.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 619 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00619
Opus 5 $0.00000 $0.00309
Sonnet 5 $0.00000 $0.00124
Haiku 4.5 $0.00000 $0.00062

Measured 5d ago against content hash 8d9d7e276c11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

launch-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 5d 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.

.claude/skills/launch-checklist/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Launch Checklist

Trigger

Activate on "launch checklist", "pre-launch check", "ready to launch?", "launch prep".

Behavior

Step 1: Get Context

Ask:

  1. What are you launching?
  2. Launch date
  3. How many users affected?
  4. Risk level (high/medium/low)

Step 2: Generate Checklist

Pre-Launch

  • Feature complete and QA'd
  • Rollback plan documented and tested
  • Success metrics defined with baselines
  • Monitoring dashboards set up
  • Support team briefed with FAQ
  • Release notes drafted
  • Feature flag configured (if gradual rollout)

Launch Day

  • Deploy during low-traffic window
  • Verify metrics are tracking
  • Monitor error rates for 2 hours
  • Send internal launch comms
  • Publish release notes

Post-Launch (48 hours)

  • Check primary metric vs baseline
  • Check guardrail metrics
  • Review support tickets for new issues
  • Share initial results with team

Post-Launch (1 week)

  • Full metrics review
  • Ship or iterate decision
  • Retrospective if needed

Risk Scaling

Scale the checklist to risk level:

Risk Level When What to Add
Low Config change, copy update, small UI tweak Minimal — deploy, monitor for 30 min, done
Medium New feature behind flag, migration with rollback Full checklist above. 2-hour monitoring window
High Pricing change, auth flow, data migration, public-facing API Everything above PLUS: staged rollout (1% → 10% → 50% → 100%), war room channel, exec notification, 24-hour monitoring

Example: Good vs Bad Launch Checklist Items

Bad: "Make sure everything works" Good: "Verify signup flow completes end-to-end in staging (email → verification → first dashboard load). Test with Gmail, Outlook, and corporate SSO."

Bad: "Tell the team" Good: "Post in #eng-launches: what shipped, who's on-call, rollback command, link to monitoring dashboard."

Bad: "Watch metrics" Good: "Monitor error rate in Datadog for 2 hours post-deploy. Baseline: 0.3%. Alert threshold: 0.5%. Rollback threshold: 1.0%."

Read the full file on GitHub · 71 lines

Changes

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.

  1. 5d ago First seen · 71 lines · 0 tokens per session scan A 8d9d7e276c11

Subscribe to this mod's changes

launch-checklist is a skill published in the GitHub repository aakashg/pm-claude-code-setup (152 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 619 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 2026-08-30.