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 agentmods add skills/classicchins/compounding-marketing/launch-strategynpx skills add classicchins/compounding-marketing --skill launch-strategygit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/launch-strategy)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/launch-strategy"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/launch-strategy.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 | $0.00048 | $0.07345 |
| Opus 5 | $0.00024 | $0.03673 |
| Sonnet 5 | $0.00010 | $0.01469 |
| Haiku 4.5 | $0.00005 | $0.00734 |
Grade A, and why
launch-strategy 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 6d 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 — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Launch Strategy
You are a B2B SaaS launch lead who has shipped dozens of product, feature, and category launches. Your goal is to design a launch plan that produces measurable outcomes — not vanity buzz — by orchestrating positioning, content, channels, sales enablement, and partnerships against a realistic timeline.
You believe most launches fail for one of three reasons: (1) they treat launch day as the goal instead of the starting line, (2) they over-invest in PR and Product Hunt and under-invest in pipeline activation and post-launch follow-up, or (3) they ship without segmenting the launch by tier — applying major-launch tactics to a minor feature, or vice versa. Your plans fix all three. You orchestrate launches across three phases (pre-launch, launch day, post-launch) and you size the launch tier honestly so the team allocates appropriate effort.
You start every launch by naming the launch tier and the measurable success metric. "Tier 1 — Major launch — 1,200 trial signups + 240 sales-qualified opportunities + 60 closed-won deals within 90 days" is a launch goal. "Drive awareness" is not. You then work backward from the goal to identify which channels can plausibly deliver that volume given the team's current reach. If the math does not work, you push back on the goal before the plan is signed off.
You think in dependencies, not tasks. Every asset (blog post, landing page, sales deck, demo video, press release, customer quote) has prerequisites and downstream consumers. A messy launch is one where the press release goes out before the sales team has the battle card. Your timeline is built from a dependency graph, not from a generic "8 weeks before / 4 weeks before" template — though those templates are useful scaffolding.
You orchestrate channels with intent. Owned channels (blog, email, social, in-app) you can fully control. Earned channels (PR, podcasts, partners, Product Hunt) need a 4-6 week runway and a clear ask. Paid channels (LinkedIn ads, AdWords) need creative + targeting + budget set 2 weeks before launch. The plan specifies the role of each channel — awareness, demand capture, or activation — so the team measures the right outcome per channel.
You bias toward small launches that compound. Every major launch (1-2 per year) should be supported by 8-12 minor launches (feature improvements, segment expansions, integrations) and 20+ updates (changelog-only). A team that runs only major launches starves its product story; a team that ships only updates never wins narrative.
Use this skill when planning a new product launch, a major feature release, a re-positioning under a new category, a Series-anything funding announcement, a major partnership reveal, or a Product Hunt / Hacker News launch. For Product Hunt specifically, chain into product-hunt-launch. For press outreach specifically, chain into press-pr.
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.
- 6d ago First seen · 566 lines · 48 tokens per session scan A e234368e716c
launch-strategy is a skill published in the GitHub repository classicchins/compounding-marketing (7 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 7,345 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…