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.
npx agentmods add agents/fmarzochi/egc/harness-optimizergit clone --depth 1 https://github.com/Fmarzochi/EGCWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/fmarzochi/egc/harness-optimizer)<a href="https://agentmods.dev/agents/fmarzochi/egc/harness-optimizer"><img src="https://agentmods.dev/badge/agents/fmarzochi/egc/harness-optimizer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once 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 |
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 4d 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.
This is a copy
91% 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.
What it actually says
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).
- Propose minimal, reversible configuration changes.
- Apply changes and run validation.
- Report before/after deltas.
Constraints
- Prefer small changes with measurable effect.
- Preserve cross-platform behavior.
- Avoid introducing fragile shell quoting.
- Keep compatibility across Gemini Code, Cursor, OpenCode, and Codex.
Output
- baseline scorecard
- applied changes
- measured improvements
- remaining risks
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.
- 4d ago First seen · 35 lines · 21 tokens per session scan A 9321781740b3
harness-optimizer is an agent published in the GitHub repository Fmarzochi/EGC (48 stars, last pushed today), licensed Apache-2.0. 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 91% identical to harness-optimizer, differing in 2 lines, and is treated as a copy.
Other agents, from other repositories
test-hunter
Generates adversarial tests for a module or feature. Does NOT write happy-path tests — that is the author's job. Finds inputs that break contracts, bypass permissions, trigger race conditions, or violate invariants. Invoke when a module has a base suite and needs adversarial hardening, before merging a sensitive…
change-reviewer
Reviews structural changes (new modules, refactors, schema changes) for architecture conformance, naming conventions, layer violations, and missing ADRs. Invoke when a PR touches architecture, data model, or adds a new domain module.
security-reviewer
Reviews code changes for security issues: credential leaks, auth bypass, missing input validation, unsafe operations, and violations of operation-classification.md. Invoke before merging PRs that touch auth, API routes, or credential handling.
spec-guardian
Verifies the codebase is in sync with the spec (PRD.md, use-cases.md, ADRs, data-model.md). Detects derivation gaps — code that contradicts the spec, spec that has no implementation, and structural decisions without an ADR. Invoke before cutting a release or when drift is suspected.
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?
default_agents
Reference implementations of default agents designed around different functional focuses and reasoning patterns.