Harness Optimizer — Development agent for Claude Code
Analyze and improve the local agent harness configuration for reliability, cost, and throughput.
How to install Harness Optimizer
Installs to ~/.claude/agents/ysyecust-everything-claude-code-harness-optimizer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ysyecust/everything-claude-code/HEAD/agents/harness-optimizer.md -o ~/.claude/agents/ysyecust-everything-claude-code-harness-optimizer.md Restart Claude Code, or start a new session, for it to be picked up.
What Harness Optimizer does
name: harness-optimizer description: Analyze and improve the local agent harness configuration for reliability, cost, and throughput. tools: ["Read", "Grep", "Glob", "Bash", "Edit"] model: sonnet color: teal
You are the harness optimizer.
Mission
Raise agent completion quality by improving harness configuration, not by rewriting product code.
Workflow
- Run
/harness-auditand collect baseline score. - Identify top 3 leverage areas (hooks, evals, routing, context, safety).
Alternatives in Development
- SLO Implement — You are an SLO (Service Level Objective) expert specializing in implementing reliability standards a... - wsho 31.9k ★
- Optimizer — Phase 6: Description Optimizer Agent 465 ★
- Doctrine Performance Optimizer 206 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Code Cleanup Optimizer
Remove technical debt, improve quality, eliminate redundancy after implementation is verified. Never use befor
Budget Optimizer
Finds wasted spend and winners across platforms, then reallocates budget by ROAS, tunes bids, and kills losers
Reliability Analyst
Use this agent when the user explicitly requests interpretation of an existing agent-evals report. Never launc
Agent Harness Optimizer
Context window, token budget, and agent harness optimization specialist. Analyzes transcript bloat, tunes prom
Deco Optimizer
Reviews Deco mesh configuration and placement, and proposes concrete tuning - node placement, band and channel
Agent Docs Writer
Use this agent when you need to create or improve technical documentation for Claude Code agents, including sy
Related Skills
Shellbench
The agent benchmark that scores the full stack — harness, config, and model — not just the LLM. Trace-based sc
Agent Eval Hub
Multi-provider + cross-device reliability harness for AI agents. Runs the same suite across Claude, OpenAI, Ge
Agent Reliability Harness
Evals, tracing and CI regression gates for tool-using agents: tool-selection, final-state, cost, latency and s
