harness-optimizer

An agent that examines and adjusts the configuration around a coding agent, such as its hooks, evaluations, routing, context, and safety settings. It changes the agent setup rather than the product code.

In plain words
What is it for?
Use it to audit a local agent setup, propose and apply reversible configuration changes, validate them, and report the before-and-after results and remaining risks.
Why use it?
It helps find configuration choices that reduce reliability, increase cost, or slow completion, then checks whether small changes improve the results.

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/mturac/everything-openai-codex/harness-optimizer
Clone the repo
git clone --depth 1 https://github.com/mturac/everything-openai-codex
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 183 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 94% 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 $0.00183
Opus 5 $0.00010 $0.00092
Sonnet 5 $0.00004 $0.00037
Haiku 4.5 $0.00002 $0.00018

Measured 2d ago against content hash e19417eb4798, 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

94% identical to harness-optimizer — 2 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 OpenAI Codex, 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 e19417eb4798

Subscribe to this mod's changes

harness-optimizer is an agent published in the GitHub repository mturac/everything-openai-codex (89 stars, last pushed 8d ago), licensed MIT. It adds 21 tokens to every session and 183 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to harness-optimizer, differing in 2 lines, and is treated as a copy.