harness-optimizer

A tool for checking and adjusting the settings that control how local coding agents work. It focuses on reliability, cost, speed, safety, and compatibility across several agent applications.

In plain words
What is it for?
Use it to audit hooks, tests, task routing, context handling, and safety settings, then apply and validate configuration changes.
Why use it?
It helps find configuration choices that make agents fail, run slowly, cost more, or behave inconsistently. Changes are kept small, reversible, and measured before and after.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/ysyecust/everything-claude-code/harness-optimizer
Clone the repo
git clone --depth 1 https://github.com/ysyecust/everything-claude-code
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00181
Opus 5 $0.00010 $0.00090
Sonnet 5 $0.00004 $0.00036
Haiku 4.5 $0.00002 $0.00018

Measured 2d ago against content hash 4f93d025ee77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-optimizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to harness-optimizer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.kiro/agents/harness-optimizer.md · 35 lines

What it actually says

You are the harness optimizer.

Mission

Raise agent completion quality by improving harness configuration, not by rewriting product code.

Workflow

  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.

Constraints

  • Prefer small changes with measurable effect.
  • Preserve cross-platform behavior.
  • Avoid introducing fragile shell quoting.
  • Keep compatibility across Claude Code, Cursor, OpenCode, and Codex.

Output

  • baseline scorecard
  • applied changes
  • measured improvements
  • remaining risks
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 35 lines · 21 tokens per session scan A 4f93d025ee77

Subscribe to this mod's changes

harness-optimizer is an agent published in the GitHub repository ysyecust/everything-claude-code (43 stars, last pushed 15d ago), licensed MIT. It adds 21 tokens to every session and 181 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to harness-optimizer, differing in 0 lines, and is treated as a copy.