From harness
Use every time a new model lands (Opus / Sonnet / Haiku release, or a meaningful provider change). Triggers on "/re-assess-harness", "the new model is out — what should we strip", "re-evaluate the harness", "is X still needed in the harness". Strips scaffolding that no longer earns its cost; flags capabilities now unlocked.
How this skill is triggered — by the user, by Claude, or both
Slash command
/harness:re-assess-harnessThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Every harness component encodes an assumption about what the current model can't do. Model releases close some of those gaps. Run this skill on every project that has a `.harness/` whenever a model lands.
Every harness component encodes an assumption about what the current model can't do. Model releases close some of those gaps. Run this skill on every project that has a .harness/ whenever a model lands.
Rule of thumb: strip first, add later. The path from Opus 4.5 to 4.6 dropped sprint decomposition AND per-sprint evaluation. The path forward looks similar — fewer scaffolding components, not more.
For each component, ask: "Does the new model still need this?" If no, remove. If unsure, A/B test.
harness_version in config.json.harness_version. Document each stripped component in progress.jsonl with the A/B evidence.A re-assessment that:
harness_version cleanly.npx claudepluginhub kamilseghrouchni/harness --plugin harnessCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.