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/yasuui/ystack/launch-skillnpx skills add Yasuui/ystack --skill launch-skillgit clone --depth 1 https://github.com/Yasuui/ystackWhat 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 | $0.00076 | $0.01785 |
| Opus 5 | $0.00038 | $0.00892 |
| Sonnet 5 | $0.00015 | $0.00357 |
| Haiku 4.5 | $0.00008 | $0.00178 |
Grade A, and why
launch-skill 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 yesterday.
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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Skill
The Launch Is Not a Moment
Launches fail when treated as a single event.
A launch is a 7-day arc:
- Day -3: Seed
- Day -1: Prime
- Day 0: Publish
- Day 1: Amplify
- Day 3: Follow-up
- Day 7: Compound
Asset Sequence
Produce assets in this order. Never skip a step.
Step 1: The end frame first
Build the one image you want people to screenshot and share. For ystack: the comparison table. For Focused AI: the overlay screenshot with real insights. For Lumina: the command centre with real account data.
This image is not made last. It is made first. Every other asset exists to point to it.
Step 2: The README hero
The GitHub README is the landing page. Before posting anywhere, the README needs:
- Hero image (1200×630 Nano Banana graphic) — captures the aesthetic
- One-liner headline — what it is, for whom, in one sentence
- The comparison or differentiation table (if applicable)
- Install command that fits on one line
- 3–5 key features, specific (numbers where possible)
- Screenshot or screen recording embedded
Step 3: Remotion X post video
The comparison or launch video. 15 seconds. Referenced in the first X post.
Step 4: Substack header
If launching via Standard Bio., the cover image is required before writing.
Step 5: Copy — post by post
Write each post in the sequence below. Do not write them all at once.
Day -3: Seed
Plant early signals without announcing. The goal is discovery by the people most likely to care.
GitHub:
- Push the repo with a clean README
- Pin the repo on your profile
- Set the social preview: Settings → General → Social preview → upload hero image
- Add topics:
ai,open-source,gemini,developer-tools,typescript(whatever applies)
X: Post one observation without mentioning your project.
"Gemini CLI is underrated. 1M context window, free tier, function calling.
Most people are still sleeping on it."
No link. No product mention. Just signal.
Day -1: Prime
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.
- yesterday First seen · 241 lines · 76 tokens per session scan A f93ab2186596
launch-skill is a skill published in the GitHub repository Yasuui/ystack (1 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 1,785 once invoked, about $0.0004 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
env-scanner
Scan and audit Gemini CLI, Claude Code, Antigravity, Continue, Windsurf, JetBrains AI, and OpenCode environments. Discovers configurations, audits memory tiers, detects skill extraction state, analyzes behavioral tool chains, checks policy governance (v0.40+), and suggests reusable skills with evidence gating.…
scan
Scan your AI coding tool ecosystem — Gemini CLI, Claude Code, Antigravity (Desktop, CLI, IDE), Continue, Windsurf, JetBrains AI, OpenCode. Produces a maturity score, advisory recommendations, and optionally generates reusable SKILL.md files from your conversation patterns. Use when the user asks to audit their…
youtube-shorts-generator
Generate viral 9:16 YouTube Shorts (or TikTok/Reels clips) from a long-form YouTube URL or local video. Triggers on requests like "make shorts from this video", "extract viral clips from this YouTube link", "auto-clip this podcast", "find the best moments and crop vertical". Pipeline downloads the source, transcribes…
looker
These skills are designed for data discovery and business intelligence.
google-cloud-storage-bucket-architect
Creates Cloud Storage (Google Cloud Storage, or GCS) buckets. Analyzes the workload (sensitive data, media hosting, ingestion, web hosting, archiving, backup, logging, analytics, AI/ML, or general-purpose), validates project-level security settings, and designs a secure-by-default, cost-effective configuration…
looker-dev
These skills are built for LookML developers, data engineers, and administrators who manage the backbone of Looker.