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 instructions/yshishenya/stitchflow/gemini-mdgit clone --depth 1 https://github.com/yshishenya/stitchflowWrote 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/instructions/yshishenya/stitchflow/gemini-md)<a href="https://agentmods.dev/instructions/yshishenya/stitchflow/gemini-md"><img src="https://agentmods.dev/badge/instructions/yshishenya/stitchflow/gemini-md.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 | $0.00497 | $0.00497 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00099 | $0.00099 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
stitchflow GEMINI.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
StitchFlow for Gemini CLI
Use this extension when the user wants to turn a product brief, mockup, or UI idea into a generated screen, a refined screen edit, or a set of visual variants with local HTML and screenshots.
The repository ships a canonical agent skill at skills/stitchflow/, keeps skills/stitch-design-local/ as a legacy alias, and includes a local toolkit at stitch-starter/.
When to use StitchFlow
- The user wants UI exploration before implementation
- The user wants prompt-to-HTML output
- The user wants multiple visual directions for the same screen
- The user wants local screenshots and artifacts saved on disk
Local setup
- Clone the repository.
- Run
bash install.sh --target allfor the canonical local install. - Add
STITCH_API_KEYto${STITCH_STARTER_ROOT:-$HOME/.agents/stitch-starter}/.env. - Restart Gemini CLI if needed.
Working rules
- Rewrite vague UI requests into a stronger design prompt before running Stitch.
- Prefer desktop web unless the user clearly asks for mobile or tablet.
- For first-pass exploration, prefer one generated screen and then three variants.
- If the user already has a close screen, prefer targeted edits over regeneration.
- Always report where HTML, screenshots, and run metadata were saved.
- Never print or expose
STITCH_API_KEYor.envcontents.
Toolkit commands
Run commands inside ${STITCH_STARTER_ROOT:-$HOME/.agents/stitch-starter}.
Generate a new screen:
npm run generate -- --prompt "A premium desktop analytics dashboard for a product team"
Edit the latest screen:
npm run edit -- --prompt "Make it more premium and improve typography hierarchy"
Create variants:
npm run variants -- --prompt "Explore three stronger visual directions" --variant-count 3
List projects and screens:
npm run list
Output paths
- Runs are saved under
${STITCH_STARTER_ROOT:-$HOME/.agents/stitch-starter}/runs/ - Latest single-screen pointer:
${STITCH_STARTER_ROOT:-$HOME/.agents/stitch-starter}/runs/latest-screen.json
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.
- 5d ago First seen · 64 lines · 497 tokens per session scan A 7569191d35d7
stitchflow GEMINI.md is an instructions file published in the GitHub repository yshishenya/stitchflow (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 497 tokens to every session, about $0.0025 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 instructions, from other repositories
librefang AGENTS.md
AGENTS.md instructions for librefang/librefang, covering stack, layout, build, architecture and kernelhandle trait.
autonomous-os AGENTS.md
AGENTS.md instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
OneManCompany CLAUDE.md
Instructions for 1mancompany/OneManCompany, covering gstack and skill routing.
souls-directory CLAUDE.md
Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.
jentic-one GEMINI.md
Gemini CLI instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
clawock AGENTS.md
AGENTS.md instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.