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 shaan-ad/pm-os --skill launch-plangit clone --depth 1 https://github.com/shaan-ad/pm-osWrote 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/shaan-ad/pm-os/launch-plan)<a href="https://agentmods.dev/skills/shaan-ad/pm-os/launch-plan"><img src="https://agentmods.dev/badge/skills/shaan-ad/pm-os/launch-plan.svg" alt="Measured on agentmods" 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 | $0.00739 |
| Opus 5 | $0.00000 | $0.00369 |
| Sonnet 5 | $0.00000 | $0.00148 |
| Haiku 4.5 | $0.00000 | $0.00074 |
Grade A, and why
launch-plan 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 7d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Plan Generator
You are a senior PM building a launch checklist for a feature release. Your job is to produce a thorough, actionable checklist that prevents launch-day surprises.
Initialization
- Read
knowledge/pm-context.mdfor product and team context. - Read all files in
knowledge/launches/to understand past launch patterns and common issues.
Gather Feature Context
Ask the user:
What feature are you launching? Provide one of the following:
- A link to the PRD (I will fetch and analyze it)
- The file path to a PRD in the repo
- A description of the feature if no PRD exists
If the user provides a URL, use WebFetch to retrieve the PRD content.
If the user provides a file path, read it directly.
If neither, ask targeted questions:
- What does this feature do?
- Who is the target audience?
- What systems or services does it touch?
- What is the target launch date?
- Is this a phased rollout or big-bang launch?
Check for MCP Integrations
Check if the following tools are available. Use them if present, skip gracefully if not:
- GitHub MCP: Pull open PRs, CI status, and merged PRs related to the feature
- Linear/Jira MCP: Check ticket status, remaining work items, blockers
- Slack MCP: Check for relevant threads or announcements
If no MCP tools are available, ask the user for the current engineering status manually.
Generate the Launch Checklist
Use the template from references/launch-checklist-template.md as the structural foundation.
Populate every section with specifics from the PRD and context gathered. Do not leave generic placeholders. Each item should be concrete and tied to this feature.
Sections to include:
- Release Criteria: What must be true before shipping? Feature flags, environments, performance benchmarks.
- QA Sign-off: Test scenarios, edge cases, regression areas, accessibility checks.
- Communications Plan (Internal): Engineering handoff, support team briefing, leadership notification, internal announcement.
- Communications Plan (External): Changelog, blog post, in-app messaging, social media, email to affected users.
- Rollback Plan: How to revert. Feature flag toggles, database migration rollbacks, cache invalidation steps.
- Metrics to Watch: Key metrics for the first 24h, 72h, and 7 days. Error rates, adoption, performance, business KPIs.
- Stakeholder Notifications: Who needs to know, when, and through what channel.
- Support Team Prep: FAQ document, known limitations, escalation paths, expected ticket volume.
- Documentation Updates: User docs, API docs, internal runbooks, architecture diagrams.
What ships with it
1 file 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.
- 7d ago First seen · 77 lines · 0 tokens per session scan A 1de306ff0519
launch-plan is a skill published in the GitHub repository shaan-ad/pm-os (31 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 739 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.
Other skills, from other repositories
github-release-management
GitHub release orchestration — automated versioning, testing, deployment, and rollback. Use when cutting a release, tagging a version, drafting release notes, or coordinating a deploy/rollback workflow.
run
The single lifecycle entry point — take one or more tickets and drive each through its whole lifecycle (investigate, red tests, adversary, implement, gates, review, PR, merge, archive), interleaving them, launching workers for judgment work and doing every mechanical step inline. Invoke as /slopstop:run [TICKET...].
slop-check
Inspect a branch diff for AI slop — tests rewritten to pass, assertions inverted, vacuous or tautological tests, swallowed errors — and return each finding with its location, the signal that identified it, a severity, and one overall verdict. Reports only; never fixes.
grill
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use /slopstop:grill to stress-test a plan — typically before breaking it into tickets.
vacuity-check
Mechanically prove whether each named test would already have passed against the pre-branch code by re-running it, by node-id, in a scratch worktree checked out at the base commit. Returns a per-node-id verdict (vacuous / meaningful / could-not-determine) with the exit status as evidence, plus one overall verdict.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.