stitchfy CLAUDE.md

Project instructions for Stitchfy, a command-line pipeline that turns a Markdown brief into a static website. They document its commands, generated outputs, validation steps, and required environment settings.

In plain words
What is it for?
Use them to run the full pipeline, build a site from a blueprint, generate a Stitch site, audit accessibility and search-engine settings, validate inputs, and check TypeScript.
Why use it?
They give an agent the correct commands and workflow for running Stitchfy without guessing how its blueprint and website-generation stages fit together. They also identify the main correctness check: TypeScript validation.

Instructions file

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/devifyllc/stitchfy/claude-md
Clone the repo
git clone --depth 1 https://github.com/devifyllc/stitchfy
Per session 1,331 This file is loaded in full into every session.
When invoked 1,331 The same file — it is already loaded in full.
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 $0.01331 $0.01331
Opus 5 $0.00665 $0.00665
Sonnet 5 $0.00266 $0.00266
Haiku 4.5 $0.00133 $0.00133

Measured 2d ago against content hash b99e3ad09fc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stitchfy CLAUDE.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 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.

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.

CLAUDE.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

npm run stitchfy                              # Run full agent pipeline on input/project.md
npm run stitchfy -- --input path/to/file.md  # Run pipeline on a specific input file
npm run build:site                            # Template generator → output/static-site/
npm run build:site -- --blueprint path/to/blueprint.json
npm run build:site:stitch                     # Stitch MCP generator → output/stitch-site/
npm run audit                                 # HTML accessibility + SEO audit → output/reports/
npm run validate                              # Validate input file and last generated blueprint
npm run typecheck                             # TypeScript check without emitting

There is no test suite. npm run typecheck is the primary correctness gate before submitting changes.

build:site:stitch requires STITCH_API_KEY in .env. Optional: STITCH_MODEL (GEMINI_3_1_PRO default, or GEMINI_3_FLASH).

Architecture

Stitchfy is a CLI framework: one Markdown file in → one static website out. There is no web server, no database, and no runtime.

Pipeline flow — blueprint (shared)

input/project.md
  → markdown-parser.ts       (ParsedMarkdown)
  → orchestrator.ts          (drives 5 agents sequentially via agent-runner.ts)
  → [intake → ux → seo → accessibility → frontend agents]
  → blueprint.schema.ts      (Zod validation)
  → blueprint-writer.ts      (output/blueprint/website-blueprint.v1.json)

Pipeline flow — template generator (build:site)

website-blueprint.v1.json
  → site-generator.ts        (output/generated-site/ — full Next.js 14 app)
  → Next.js export           (output/static-site/ — deployable HTML/CSS/JS)

Pipeline flow — Stitch generator (build:site:stitch)

website-blueprint.v1.json
  → stitch-client.ts         (create_project → generate_screen_from_text per page → get_screen)
  → stitch-post-processor.ts (inject SEO meta, skip link, lang, JSON-LD)
  → stitch-seo.agent.ts      (review SEO → patches + findings)
  → stitch-a11y.agent.ts     (review A11y → patches + findings)
  → stitch-patcher.ts        (apply all attribute-level patches)
  → output/stitch-site/      (deployable HTML/CSS/JS)
  → stitch-review-reporter.ts → output/reports/stitch-review-report.html

Read the full file on GitHub · 95 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 · 95 lines · 1,331 tokens per session scan A b99e3ad09fc4

Subscribe to this mod's changes

stitchfy CLAUDE.md is an instructions file published in the GitHub repository devifyllc/stitchfy (47 stars, last pushed 13d ago), licensed Apache-2.0. It adds 1,331 tokens to every session, about $0.0067 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.