stitch-kit AGENTS.md

A contributor guide for Stitch Kit, a collection of packaged instructions and scripts that help AI agents create and revise user interfaces using Stitch. It also describes how each skill is organised and installed for several coding-agent tools.

In plain words
What is it for?
Use it when adding or maintaining Stitch skills, design workflows, design-token extraction, or conversions to different web frameworks.
Why use it?
It explains the repository's structure and the practical details of working with Stitch, including reusable examples and scripts. This saves developers from learning each skill's conventions from scratch.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/gabelul/stitch-kit/agents-md
Clone the repo
git clone --depth 1 https://github.com/gabelul/stitch-kit

Made for: Codex, OpenCode.

Per session 1,673 This file is loaded in full into every session.
When invoked 1,673 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01673 $0.01673
Opus 5 $0.00837 $0.00837
Sonnet 5 $0.00335 $0.00335
Haiku 4.5 $0.00167 $0.00167

Measured 2d ago against content hash 93353d6e0775, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

stitch-kit AGENTS.md scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Then wire up Stitch MCP in `~/.codex/config.toml`:
AGENTS.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for Claude Code, Cursor, Copilot, Codex CLI, and other AI agents working with this plugin.

What this repo is

A collection of Claude Code skills — 36 packaged instructions and scripts that extend AI agents with Stitch-specific capabilities: text-to-UI generation, design iteration (edit, variants, design systems), design token extraction, and multi-framework conversion. Think of it as a Stitch co-pilot that wraps all 15 Stitch MCP tools and knows the footguns so you don't have to learn them the hard way.

Skill structure

Each skill directory follows the Agent Skills standard:

skills/{skill-name}/
├── SKILL.md              ← Required: activation instructions and workflow
├── examples/             ← Required: worked examples (gold-standard reference)
├── resources/            ← Optional: templates, checklists, mapping tables
├── scripts/              ← Optional: bash scripts (fetch-stitch.sh, init_stitch_skill.py, etc.)
└── references/           ← Optional: style guides, contracts
  • SKILL.md: YAML frontmatter (name, description, allowed-tools) + markdown instructions
  • examples/: Load for few-shot context when needed
  • resources/, scripts/: Progressive disclosure — reference only when relevant

Quick install (both platforms)

npx @booplex/stitch-kit

Auto-detects Claude Code and/or Codex CLI and installs to the right places. Also tells you if Stitch MCP needs configuring.

To update later: npx @booplex/stitch-kit update (npx always fetches the latest version). To check what's installed: npx @booplex/stitch-kit status.

Installing (Claude Code)

Stitch MCP first (remote HTTP server — needs an API key from stitch.withgoogle.com/settings):

claude mcp add stitch --transport http https://stitch.googleapis.com/mcp \
  --header "X-Goog-Api-Key: YOUR-API-KEY" -s user

Then the plugin:

/plugin marketplace add https://github.com/gabelul/stitch-kit.git
/plugin install stitch-kit@stitch-kit

Read the full file on GitHub · 145 lines

Changes

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.

  1. 2d ago First seen · 145 lines · 1,673 tokens per session scan B 93353d6e0775

Subscribe to this mod's changes

stitch-kit AGENTS.md is an instructions file published in the GitHub repository gabelul/stitch-kit (43 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,673 tokens to every session, about $0.0084 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.