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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/yshishenya/stitchflow/agents-md"><img src="https://agentmods.dev/badge/instructions/yshishenya/stitchflow/agents-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 | $0.00516 | $0.00516 |
| Opus 5 | $0.00258 | $0.00258 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
stitchflow AGENTS.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 4d 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.
What it actually says
StitchFlow
Cross-agent Stitch skill bundle for Codex, Claude Code, OpenClaw, GitHub Copilot, and Gemini CLI.
Repository:
What this skill is for
Use stitchflow when the task is:
- design generation from a brief or mockup
- UI prototyping from product context
- prompt-to-HTML workflows
- screen edits and visual iteration
- design variants before implementation
- local screenshots and Tailwind-friendly HTML exports
Install
git clone https://github.com/yshishenya/stitchflow.git
cd stitchflow
bash install.sh --target all
Canonical install layout:
- skill:
~/.agents/skills/stitchflow - toolkit:
~/.agents/stitch-starter
Native compatibility links:
- Codex:
~/.codex/skills/stitchflow - Claude Code:
~/.claude/skills/stitchflow - OpenClaw:
~/.openclaw/skills/stitchflow - GitHub Copilot:
~/.copilot/skills/stitchflow - legacy alias still installed:
stitch-design-local
Native extension / plugin packaging:
- GitHub Copilot plugin manifest:
.github/plugin/plugin.json - Gemini CLI extension manifest:
gemini-extension.json
How to use
- explicit invocation:
Use $stitchflow ... - common jobs: generate a new screen, edit an existing screen, create variants, export local artifacts
- toolkit root:
${STITCH_STARTER_ROOT:-$HOME/.agents/stitch-starter} - brand:
StitchFlow - legacy alias:
stitch-design-local
Skill
- name:
stitchflow - location:
skills/stitchflow - install command:
bash install.sh --target all
Metadata files
- root discovery: README.md
- agent bundle: skills/stitchflow/SKILL.md
- Codex metadata: skills/stitchflow/agents/openai.yaml
- Claude metadata: .claude-plugin/plugin.json
- GitHub Copilot metadata: .github/plugin/plugin.json
- Gemini CLI metadata: gemini-extension.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.
- 4d ago First seen · 68 lines · 516 tokens per session scan A 5dd8ef6243f2
stitchflow AGENTS.md is an instructions file published in the GitHub repository yshishenya/stitchflow (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 516 tokens to every session, about $0.0026 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
unity-ui-toolkit-design-system AGENTS.md
Instructions for sinanata/unity-ui-toolkit-design-system, covering agents.md, what this project is, golden rules (do not violate), use the design system in your project and repository layout.
unity-ui-toolkit-design-system copilot-instructions.md
Instructions for sinanata/unity-ui-toolkit-design-system: This repository follows the cross-tool AGENTS.md standard. Read /AGENTS.md for the full guide: the ds- class naming, the token rules, the load-bearing USS import order, build and preview commands, and the pull-request checklist.
gridgeist AGENTS.md
Instructions for ohmiler/gridgeist, a project described as: Gridgeist turns product intent into a rigorous visual system—without the generic AI SaaS aftertaste.
stitch-kit AGENTS.md
Instructions for gabelul/stitch-kit, covering agents.md, what this repo is, skill structure, quick install (both platforms) and installing (claude code).
MasterGo2Figma AGENTS.md
AGENTS.md instructions for AaronXu-Lab/MasterGo2Figma, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
MasterGo2Figma CLAUDE.md
Claude Code instructions for AaronXu-Lab/MasterGo2Figma: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.