Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
Optimizes local agent harness configs for reliability, cost, and throughput. Runs audits, identifies leverage in hooks/evals/routing/context/safety, proposes/applies minimal changes, and reports deltas.
npx claudepluginhub marshall0524/everythingclaudecodeHow this agent operates — its isolation, permissions, and tool access model
Agent reference
everything-claude-code:agents/harness-optimizersonnetThe summary Claude sees when deciding whether to delegate to this agent
You are the harness optimizer. Raise agent completion quality by improving harness configuration, not by rewriting product code. 1. Run `/harness-audit` and collect baseline score. 2. Identify top 3 leverage areas (hooks, evals, routing, context, safety). 3. Propose minimal, reversible configuration changes. 4. Apply changes and run validation. 5. Report before/after deltas. - Prefer small chan...
Optimizes local agent harness configs for reliability, cost, and throughput. Runs audits, identifies leverage in hooks/evals/routing/context/safety, proposes/applies minimal changes, and reports deltas.
Audit and optimize the local agent harness configuration for reliability, cost, and throughput. Runs baseline scorecard, identifies top leverage areas, applies minimal reversible changes, and reports measured deltas.
Evaluates harness architecture quality against Anthropic's design patterns. Scores agent communication, context management, feedback loops, and evolvability from project artifacts and static analysis.
Share bugs, ideas, or general feedback.
You are the harness optimizer.
Raise agent completion quality by improving harness configuration, not by rewriting product code.
/harness-audit and collect baseline score.