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 Yasuui/ystack --skill market-skillgit clone --depth 1 https://github.com/Yasuui/ystackWrote 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/yasuui/ystack/market-skill)<a href="https://agentmods.dev/skills/yasuui/ystack/market-skill"><img src="https://agentmods.dev/badge/skills/yasuui/ystack/market-skill/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/yasuui/ystack/market-skill"><img src="https://agentmods.dev/badge/skills/yasuui/ystack/market-skill.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 | $0.00081 | $0.02458 |
| Opus 5.5 | $0.00032 | $0.00983 |
| Sonnet 5.5 | $0.00016 | $0.00492 |
| Haiku 4.5 | $0.00008 | $0.00246 |
Grade A, and why
market-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 1mo 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Market Skill
Settings
Adjust these three dials (1–10) before generating any asset:
BRAND_INTENSITY = 8 // How distinct and ownable is the visual identity?
// 1-3: Minimal, almost invisible branding
// 4-7: Balanced — clear brand without being loud
// 8-10: Strong, immediately recognisable. Every pixel serves the brand.
MOTION_DRAMA = 7 // How cinematic and choreographed is the motion?
// 1-3: Almost no animation. Typography does the work.
// 4-7: Purposeful motion. Each element earns its entrance.
// 8-10: Choreographed sequences. Apple-level timing precision.
COPY_DIRECTNESS = 8 // How confident and direct is the language?
// 1-3: Soft, benefit-focused, descriptive
// 4-7: Confident but approachable
// 8-10: Blunt, specific, zero hedging. No adjectives without proof.
Visual Identity Standards
Color
The most common mistake: using more than one accent color.
- Pick one accent. Use it as a signal, not decoration.
- The background is not
#000000. Use deep, slightly-tinted darks:#080810,#0c0c14,#0a0f0f. - Never use the generic "AI gradient" — purple-to-blue linear gradient. It signals you ran out of ideas.
- White is not
#fffffffor body text. Usergba(255,255,255,0.80)orrgba(255,255,255,0.65). Pure white on dark backgrounds is harsh. - Tint your shadows. If background is
#080810, shadows should bergba(0,0,0,0.6)with a slight blue tint — not pure black. - Glow should be subtle.
rgba(accent, 0.12)in a radial gradient at the top. Not a lighthouse. - Build a palette of 4 values: background, surface, accent, and muted text. Nothing else.
Typography
- Display text (48px+) gets
letter-spacing: -2pxto-4px. Tight headlines look considered. - Body text gets
letter-spacing: 0or very slightly positive (0.1px max). - Never mix more than two typefaces in one asset.
- Mono fonts for technical labels, file paths, version numbers, and metadata. Not for body copy.
- Line-height for headlines:
1.0to1.08. Tight. Marketing is not a blog post. - Line-height for body:
1.5to1.6. Breathing room. - Font weights: use 400 (body), 500 (sub-labels), 700 (emphasis), 800 (display). Skip 600 for display — it looks indecisive.
- All caps labels: only in mono, only for metadata-level information (version tags, dates, categories). Never all-caps for headings.
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.
- 1mo ago First seen · 208 lines · 81 tokens per session scan A 62e844dee859
market-skill is a skill published in the GitHub repository Yasuui/ystack (1 stars, last pushed 23d ago), licensed MIT. It adds 81 tokens to every session and 2,458 once invoked, about $0.0003 per session on Opus 5.5. 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…
local-places
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
issue-maintenance
Writes to a repo's open GitHub issues: fixes type and lifecycle labels, re-scores priority, fills sizing labels, cleans up issue prose, and proposes merging clusters of small issues. Auto-applies safe changes, flags the rest. Trigger on: "run issue maintenance", "tidy the backlog", "re-prioritize open issues"…
test-reaper
Finds and removes dead or trivial tests: duplicates, mock-only asserts, render checks that prove nothing. Also finds over-mocked tests and seam gaps, where no test sends a realistic payload across a boundary. Trigger on: "reap tests", "our tests don't test anything", "too much mocking", "why didn't tests catch this".