harness-optimizer

An analysis agent that reviews Claude Code tool-call logs. A harness is the project's hooks, checks, and setup around the coding agent.

In plain words
What is it for?
For suggesting hooks and checks, analyzing .claude/logs/, and improving an agent setup.
Why use it?
It helps identify setup changes based on actual usage instead of guesswork. Analysis requires logging to be enabled and enough usage data to reveal patterns.

Agent

Part of the shipwithai-starter plugin — 13 skills, 4 commands, 1 agent shipped together

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/shipwithai/shipwithai-plugins/harness-optimizer
Clone the repo
git clone --depth 1 https://github.com/ShipWithAI/shipwithai-plugins

Or install shipwithai-starter, the plugin that ships this one along with the rest of its 13 skills, 4 commands, 1 agent.

Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 228 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00075 $0.00228
Opus 5 $0.00037 $0.00114
Sonnet 5 $0.00015 $0.00046
Haiku 4.5 $0.00007 $0.00023

Measured 3d ago against content hash 4f1c014128ff, 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 3d 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.

plugins/starter/agents/harness-optimizer.md · 21 lines

What it actually says

Invoke /shipwithai-starter:optimize-harness and present the output directly to the user.

If the skill reports "Observability not enabled", explain:

  • The project needs /shipwithai-starter:setup-observability to start logging tool usage
  • After enabling, Claude Code must be used for at least 7 days before patterns can be analyzed
  • Tier 3 (Full) projects get this automatically during init; others can opt in anytime

If the skill reports "Not enough data yet", tell the user:

  • How many more days are needed
  • That the logging is already working — they just need to continue using Claude Code normally
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. 3d ago First seen · 21 lines · 75 tokens per session scan A 4f1c014128ff

Subscribe to this mod's changes

harness-optimizer is an agent published in the GitHub repository ShipWithAI/shipwithai-plugins (10 stars, last pushed 21d ago), licensed MIT. It adds 75 tokens to every session and 228 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

system-architect

Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…

rtk-ai/rtk · 0 tokens

ap-preflight-probe

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

Spielewoy/autoprompt-skill · 39 tokens

ijfw-assumptions-analyzer

Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?

FerroxLabs/ijfw · 34 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

ring:streaming-reviewer

Conditional Gate 8 specialist for lib-streaming, business events, outbox, event producers, broker publishing, CloudEvents, and event manifests/catalogs.

LerianStudio/ring · 38 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens