How Claude Code Subagents Wrote 13 Custom Tools Across 7 Tasks
yb2698 · x · 2026-10-24
The harness2 reproduction thread details its setup: every task starts from the same bare harness (IPython kernel, 0 tools, 278-word prompt). Claude Code subagents then write custom Python tools and a new system prompt per task, without being given task solutions. The result: 13 tools across 7 tasks (proteinfasta, zipextract, checksqlrewrite, etc.) with 278–457-word prompts.
Related event: Reproducing Google's harness2: Qwen3-9B pass rate jumps from 31% to 45%(6 posts)→
More from coding & agent
- A 2-person AI team built its own video tool and dropped Zoom entirely — danshipper · 2026-10-24
- Agent posting safety: publish, fetch as a stranger, then assert on what's actually there — petrusenko_max · 2026-10-24
- Testing your agent's public output: publish, fetch logged-out, then assert — petrusenko_max · 2026-10-24
- 100% test coverage, zero bugs found: why this dev added live-post verification — petrusenko_max · 2026-10-24
- Claude approved its own broken 3D screenshots — how a 480Hz verification gate fixed agent self-grading — youthanasia669 · 2026-10-24
- PM's step-by-step guide to building product strategy with Claude Code in 2 hours — aakashgupta · 2026-10-24