stitch-loop

stitch-loop is a skill for Claude Code, Codex from jh941213/codex-lattice. It costs 73 tokens per session (2,599 once invoked), scanned A, original, MIT.

An iterative workflow for generating and combining multiple web pages with Stitch, a tool for creating website screens from prompts. A baton file carries the next task from one build cycle to the next.

In plain words
What is it for?
Use it to read site and design guidance, generate pages, add them to an existing site, check them visually when possible, and prepare instructions for the next cycle.
Why use it?
It keeps multi-page website work organized across repeated generation and integration cycles instead of treating each page as an isolated task.

Skill for Claude CodeCodex

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 skills/jh941213/codex-lattice/stitch-loop
Any agent
npx skills add jh941213/codex-lattice --skill stitch-loop
Clone the repo
git clone --depth 1 https://github.com/jh941213/codex-lattice

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for stitch-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/jh941213/codex-lattice/stitch-loop.svg)](https://agentmods.dev/skills/jh941213/codex-lattice/stitch-loop)
Your own site
<a href="https://agentmods.dev/skills/jh941213/codex-lattice/stitch-loop"><img src="https://agentmods.dev/badge/skills/jh941213/codex-lattice/stitch-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00073 $0.02599
Opus 5 $0.00036 $0.01300
Sonnet 5 $0.00015 $0.00520
Haiku 4.5 $0.00007 $0.00260

Measured 5d ago against content hash d4ab8caa6913, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stitch-loop 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.

skills/stitch-loop/SKILL.md · 305 lines

How it starts

The opening of the file, as written. The whole thing — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stitch Build Loop

당신은 반복적인 사이트 빌드 루프에 참여하는 자율 프론트엔드 빌더입니다. Stitch를 사용하여 페이지를 생성하고, 사이트에 통합하며, 다음 반복을 위한 지침을 준비하는 것이 목표입니다.

개요

Build Loop 패턴은 "바통" 시스템을 통해 지속적이고 자율적인 웹사이트 개발을 가능하게 합니다.

각 반복 과정:

  1. 바통 파일(next-prompt.md)에서 현재 작업 읽기
  2. Stitch MCP 도구를 사용하여 페이지 생성
  3. 페이지를 사이트 구조에 통합
  4. 다음 반복을 위해 바통 파일에 다음 작업 작성

사전 요구사항

필수:

  • Stitch MCP 서버 접근 권한
  • Stitch 프로젝트 (기존 또는 새로 생성)
  • DESIGN.md 파일 (없으면 stitch-design-md 스킬로 생성)
  • SITE.md 파일 (사이트 비전 및 로드맵 문서)

선택:

  • Chrome DevTools MCP 서버 — 생성된 페이지의 시각적 검증 가능

바통 시스템

next-prompt.md 파일은 반복 간의 릴레이 바통 역할을 합니다:

---
page: about
---

Jules.top 추적 방식을 설명하는 페이지입니다.

**디자인 시스템 (필수):**
[DESIGN.md 섹션 6에서 복사]

**페이지 구조:**
1. 네비게이션이 있는 헤더
2. 추적 방법론 설명
3. 링크가 있는 푸터

중요 규칙:

  • YAML frontmatter의 page 필드가 출력 파일명 결정
  • 프롬프트 내용에 DESIGN.md의 디자인 시스템 블록 포함 필수
  • 작업 완료 전 이 파일을 업데이트하여 루프 지속

실행 프로토콜

Step 1: 바통 읽기

next-prompt.md를 파싱하여 추출:

  • page frontmatter 필드에서 페이지 이름
  • markdown 본문에서 프롬프트 내용

Step 2: 컨텍스트 파일 참조

생성 전에 다음 파일 읽기:

파일 목적
SITE.md 사이트 비전, Stitch Project ID, 기존 페이지(사이트맵), 로드맵
DESIGN.md Stitch 프롬프트에 필요한 시각적 스타일

중요 확인사항:

  • 섹션 4 (사이트맵) — 이미 존재하는 페이지를 다시 만들지 마세요
  • 섹션 5 (로드맵) — 백로그가 있으면 여기서 작업 선택
  • 섹션 6 (크리에이티브 프리덤) — 로드맵이 비어있으면 새 페이지 아이디어

Step 3: Stitch로 생성

Stitch MCP 도구를 사용하여 페이지 생성:

# 1. 네임스페이스 탐색
list_tools 실행하여 Stitch MCP 접두사 찾기

# 2. 프로젝트 가져오기 또는 생성
- stitch.json이 있으면 projectId 사용
- 없으면 [prefix]:create_project 호출 후 stitch.json에 ID 저장

# 3. 스크린 생성
[prefix]:generate_screen_from_text 호출:
- projectId: 프로젝트 ID
- prompt: 바통의 전체 프롬프트 (디자인 시스템 블록 포함)
- deviceType: DESKTOP (또는 지정된 대로)

# 4. 자산 검색
[prefix]:get_screen 호출하여:
- htmlCode.downloadUrl → queue/{page}.html로 다운로드 및 저장
- screenshot.downloadUrl → queue/{page}.png로 다운로드 및 저장

Step 4: 사이트에 통합

  1. 생성된 HTML을 queue/{page}.html에서 site/public/{page}.html로 이동
  2. 자산 경로를 public 폴더 기준 상대 경로로 수정
  3. 네비게이션 업데이트:
    • 기존 플레이스홀더 링크 (예: href="#")를 새 페이지로 연결
    • 적절한 경우 전역 네비게이션에 새 페이지 추가
  4. 모든 페이지에서 일관된 헤더/푸터 보장

Read the full file on GitHub · 305 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. 5d ago First seen · 305 lines · 73 tokens per session scan A d4ab8caa6913

Subscribe to this mod's changes

stitch-loop is a skill published in the GitHub repository jh941213/codex-lattice (19 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 2,599 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens