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 Dannykkh/skill-olympus --skill stitchgit clone --depth 1 https://github.com/Dannykkh/skill-olympusWrote 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/dannykkh/skill-olympus/stitch)<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/stitch"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/stitch/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/dannykkh/skill-olympus/stitch"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/stitch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.02053 |
| Opus 5.5 | $0.00031 | $0.00821 |
| Sonnet 5.5 | $0.00015 | $0.00411 |
| Haiku 4.5 | $0.00008 | $0.00205 |
Grade A, and why
stitch 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch
Treat Stitch as a design execution backend. Keep product structure, visual direction, and design policy in Aphrodite; use this skill to translate those decisions into Stitch operations and code artifacts.
Boundary
- Let
design-plan(/aphrodite) own discovery, IA, layout blueprints, and the rootDESIGN.md. - Let Stitch own remote project/screen operations and
.stitch/runtime state. - Let the existing application architecture own routing, state, data, and component conventions.
- Use standalone Stitch mode only when the user explicitly wants direct Stitch work without Aphrodite.
Never invent a visual direction inside this skill when DESIGN.md or docs/design-refs/ exists. Compile those artifacts into Stitch inputs.
Preflight
- Inspect the available tools and identify the Stitch MCP namespace by capability, not by a hard-coded prefix.
- Stop and report the missing dependency if no Stitch MCP tools are available. Never fabricate project IDs, screen IDs, URLs, or tool results.
- Read references/mcp-contract.md completely before any Stitch MCP call.
- Read the project root
DESIGN.mdand relevantdocs/design-refs/artifacts before generating or editing a screen. - Check
.stitch/metadata.jsonbefore remote lookup. Validate it with:
python <STITCH_SKILL_DIR>/scripts/validate_stitch_state.py .stitch/metadata.json
Resolve <STITCH_SKILL_DIR> to the directory containing this SKILL.md; do not assume the skill is installed inside the target project.
- Classify the action:
- Read-only: list/get projects, retrieve screens, download artifacts, compare state.
- Remote mutation: create/edit/vary/apply a design system.
- Sensitive upload: send a local image, HTML file, or
DESIGN.mdto Stitch.
- Treat the user's explicit request to create/edit/vary as authorization for that scoped remote mutation. Before a sensitive upload, still show the exact project, files, types, and sizes and obtain confirmation.
What ships with it
9 files 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.
- agents/openai.yaml 394 B
- references/generate-and-design-system.md 6.0 KB
- references/import-export.md 4.4 KB
- references/loop-state.md 5.3 KB
- references/mcp-contract.md 6.2 KB
- references/react-handoff.md 4.9 KB
- scripts/fetch_stitch_asset.py 3.6 KB runs code
- scripts/upload_to_stitch.py 5.6 KB runs code
- scripts/validate_stitch_state.py 4.9 KB runs code
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 · 140 lines · 77 tokens per session scan A e7a4edbb38a3
stitch is a skill published in the GitHub repository Dannykkh/skill-olympus (7 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 2,053 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 2026-09-03.
Other skills, from other repositories
design-system
Context-aware design intelligence with curated CSV databases for styles, palettes, typography, UX rules, and wow effects. Provides industry-matched color palettes, font pairings, layout patterns, spacing/radius/shadow scales, gradient recipes, micro-animations, and accessibility-safe UX rules. Stack-agnostic — outputs…
polish
Frontend quick wins to wow effects (6 dimensions). Use when: "polish", "beautify", "improve", "wow", "improve design", "enhance", "quick wins".
ss-learn
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule…
aceternity-ui
100+ animated React components (Aceternity UI) for Next.js with Tailwind. Use for hero sections, parallax, 3D effects, or encountering animation, shadcn CLI integration errors.
generic-react-ux-designer
Professional UI/UX design expertise for React applications. Covers design thinking, user psychology (Hick's/Fitts's/Jakob's Law), visual hierarchy, interaction patterns, accessibility, performance-driven design, and design critique. Use when designing features, improving UX, solving user problems, or conducting design…
generic-react-design-system
Complete design system reference for React applications. Covers colors, typography, spacing, component patterns, glassmorphism effects, GPU-accelerated animations, and WCAG AA accessibility. Use when implementing UI, choosing colors, applying spacing, creating components, or ensuring brand consistency.