Cut agent token usage by up to 90%: what RTK, Caveman and Ponytail teach about harness compression
gethackteam · x · 2026-10-24
Roy Derks (Hackteam) argues compression should be built into your agent harness. Developers keep hitting quotas on Claude, Cursor and Codex while feeding agents hundreds of lines of test output, verbose JSON, documents and inter-agent handoffs where only a fraction matters. The post walks through how RTK (up to 90% less command output), Caveman and Ponytail cut token usage without losing key context, and where compression belongs in the agent loop — reducing data before it enters the model rather than only compacting when the context window fills.
More from coding & agent
- Microsoft open-sources Agensh, a decentralized multi-agent harness scaling to 1,024 agents — donglixp · 2026-10-24
- dumbtv strips Fire TV ads and tracking with one command, no root needed — Signalman23 · 2026-10-24
- CodeRabbit CLI v0.9.0 ships cr code for managing cloud agent tasks in terminal — leslysandra · 2026-10-24
- Solo dev turns a school timetable solver into an MCP server for Claude — Wilbek_DK · 2026-10-24
- ChatGPT Sites ships detailed site analytics: dev logs +216% weekly traffic — Dimillian · 2026-10-24
- Gemini Flash-Lite as a meeting copilot brain: real test results, what worked and what broke — DeskSignalAI · 2026-10-24