使用Honey降低编码代理输出成本
Use Honey to make coding agents emit less code, less prose, and denser agent-to-agent handoffs while preserving correctness boundaries.
Prerequisites
Node.js, git or archive download fallback, and a supported agent host such as Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenClaw, Kiro, OpenCode, or Kilo Code
Installation
Use the upstream install or setup path that matches your environment:
- npm run bench makes one API call per task — clean for isolating the output lever, but it
- npx pxpipe-proxy export --json --out "$TMPDIR" src/ # → page-*.png + factsheet.txt + token report
- pip install ecologits
Requirements and caveats from upstream:
- the normative spec, JS + Python reference implementations, conformance vectors,
- need Node >= 14 on the PATH Claude Code spawns them with — desktop-app
- /usr/local/bin/node is common; the hook now warns instead of failing silently.
Basic usage or getting-started notes:
- cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs —
- (Claude Opus 4.8, 3 runs each) — run cd bench && npm run bench to reproduce.
- (npm run bench:cline) runs each task through the Cline CLI headless, so
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/Green-PT/honey-for-devs/HEAD/README.md
Documentation
- https://github.com/1991513ccie-png/skills
