agentleFS
vanzan01vanzan01/claude-agent-sdk-starter/CLAUDE.md

claude-agent-sdk-starter

CLAUDE.md9 starsChanged 10 months agoMITView on GitHub

3-stage pipeline: Researcher → Analyst → Writer

The file

Files
CLAUDE.md

Claude Agent SDK Starter

Quick Start

npm run dev          # Development mode
npm run build        # Production build

Test Pipelines

npm run test:ai-news-tweet       # 3-stage pipeline demo
npm run test:bypass-auth         # SDK auth verification
npm run test:context-window      # Verify 1M context window fix (SDK bug #35214)
npm run test:context-window:bug  # Reproduce the 200k bug (no workaround)

Project Structure

.claude/
  agents/           # Agent definitions (markdown)
  skills/           # Skill definitions with scripts
  rules/            # Auto-loaded rules for Claude Code
scripts/            # Test pipelines
src/
  main/             # Electron main process
  renderer/         # React frontend
  preload/          # IPC bridge
  shared/apps/      # App manifests

Demo App: ai-news-tweet

3-stage pipeline: Researcher → Analyst → Writer

ComponentPath
Agents.claude/agents/ai-news-tweet/
Skills.claude/skills/news-tools/, analysis-helper/, tweet-writer/
Testscripts/test-ai-news-tweet.ts

Key Rules (auto-loaded from .claude/rules/)

  • Bypass Auth: .claude/rules/core/bypass-auth.md - SDK without API key
  • App Registration: .claude/rules/development/app-registration.md - Adding new apps
  • Pipeline Patterns: .claude/rules/architecture/pipeline-patterns.md - Running agents
  • IPC Security: .claude/rules/architecture/ipc-security.md - Electron security

Verification

npm run lint && npm run typecheck && npm run build

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.