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 assimovt/productskills --skill launch-plangit clone --depth 1 https://github.com/assimovt/productskillsWrote 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/assimovt/productskills/launch-plan)<a href="https://agentmods.dev/skills/assimovt/productskills/launch-plan"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/launch-plan/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/assimovt/productskills/launch-plan"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/launch-plan.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 | $0.00057 | $0.00896 |
| Opus 5 | $0.00028 | $0.00448 |
| Sonnet 5 | $0.00011 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00090 |
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 10d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch based on the size of the bet, not the size of your ambition. Most features deserve a silent or soft launch. Save the big-bang for genuinely new products or major pivots. Linear's principle: launch early, launch often, launch multiple times.
Launch Tiers
Tier 1: Silent Launch
Ship it, turn it on, see what happens. No announcement.
Use for: Bug fixes, minor improvements, internal tools, infrastructure changes, experiments.
Checklist:
- Feature is behind a flag or gradually rolled out
- Monitoring/alerting is in place
- Rollback plan exists
- One person is on point to watch metrics for 24 hours
Tier 2: Soft Launch
Ship it, tell existing users, collect feedback before going wide.
Use for: New features for existing users, significant UX changes, pricing changes, beta programs.
Checklist:
- Changelog entry or in-app notification written
- Help docs updated (or created)
- Support team briefed with FAQ
- Feedback collection mechanism in place (survey, feedback button, Slack channel)
- Known limitations documented
- Rollback plan exists
- 1-2 week feedback period before going wide
Example: Launching real-time collaboration — Changelog: "Edit together, see cursors live." Support FAQ covers latency expectations and max concurrent editors. Roll out to 20% of teams for 3 days via feature flag, then 100%. Rollback: disable WebSocket sync, fall back to polling. Feedback widget live for 2 weeks. Success metric: % of teams with 2+ simultaneous editors.
Tier 3: Big-Bang Launch
Coordinated, public, designed for maximum reach. Expensive in time and attention.
Use for: New product launch, major pivot, rebrand, entering a new market. Maximum 2-3 per year.
Checklist:
Product
- Feature complete and tested at scale
- Onboarding flow tested with 5+ new users
- Performance benchmarked under expected load
Content
- Landing page or product page live
- Blog post / announcement written
- Demo video or screenshots prepared
- Social posts drafted for launch day and day +1, +3, +7
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.
- 10d ago First seen · 97 lines · 57 tokens per session scan A 91bcea359489
launch-plan is a skill published in the GitHub repository assimovt/productskills (68 stars, last pushed 6mo ago), licensed MIT. It adds 57 tokens to every session and 896 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…
execute-fleet
Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.