Directory · Subagents
Claude Code Engineering Harness
A CLAUDE.md template and hook setup for running Claude Code with lean context, cheaper subagents, and multi-model review.
★ 223 stars · last updated 2026-04-19 · Free (check license) · View on GitHub
Best for
- Heavy daily Claude Code users trying to avoid quota limits
- Delegating grep, research, and test work to Sonnet/Haiku subagents
- Adding mandatory verification steps and fix-size guardrails
- Setting up persistent memory and decision tracking across sessions
Install
Copy the `CLAUDE_EXAMPLE.md` file to your project root. Replace all `[Placeholders]` with your specific tech stack, ownership matrix, and verification commands. Configure your `.claude/settings.json` to include the `Stop` hooks for auto-retros.Our take
This is mainly a template CLAUDE.md plus configuration guidance, not installable software, and it has to be customized by hand. The results it claims, such as zero quota hits, come from the author's own experience and are not benchmarked. There is no license, and the optional multi-model consensus feature depends on access to Gemini plus third-party tools like claude-flow and graphify.
Similar subagents
- Awesome Claude Code Subagents (VoltAgent): A curated collection of 161+ Claude Code subagent definitions across 10 categories, installable as plugins or individual agent files.
- claude-devtools: Desktop and web app that reads local Claude Code session logs to show tool calls, token usage, subagent trees, and context.
- AI Marketing Suite for Claude Code: Claude Code skills and parallel subagents for marketing audits, copywriting, email sequences, ad copy, and client-ready reports.
- pentest-ai-agents: 50 Claude Code subagents turning Claude into an offensive security research assistant for authorized penetration testing.
- Translate Book: Agent skill for Claude Code, Codex, and OpenClaw that translates whole PDF/DOCX/EPUB books using parallel subagents per chunk.
- Claude Code Sub-Agents (lst97): A collection of 33 specialized Claude Code subagents for full-stack development, plus an agent-organizer for multi-agent orchestration.