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 skills add ryne2010/harness-engineering-audit --skill final-local-product-reviewgit clone --depth 1 https://github.com/ryne2010/harness-engineering-auditWrote 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/skills/ryne2010/harness-engineering-audit/final-local-product-review)<a href="https://agentmods.dev/skills/ryne2010/harness-engineering-audit/final-local-product-review"><img src="https://agentmods.dev/badge/skills/ryne2010/harness-engineering-audit/final-local-product-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ryne2010/harness-engineering-audit/final-local-product-review"><img src="https://agentmods.dev/badge/skills/ryne2010/harness-engineering-audit/final-local-product-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00034 | $0.00136 |
| Opus 5.5 | $0.00014 | $0.00054 |
| Sonnet 5.5 | $0.00007 | $0.00027 |
| Haiku 4.5 | $0.00003 | $0.00014 |
Grade A, and why
final-local-product-review 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 1mo 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- runtime-evidence — 92% identical, 6 lines differ
- local-mode-verification — 88% identical, 6 lines differ
What it actually says
final local product review
Follow the repository source-of-truth docs. Do not expand product scope, enable real-world effects, use real PII, or weaken tests/invariants. Produce evidence for any claim of completion.
Workflow
- Read the relevant docs/harness and product-execution contracts.
- Inspect current implementation.
- Make the smallest safe change needed for the active task.
- Run the relevant checks.
- Record evidence and 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.
- 1mo ago First seen · 17 lines · 34 tokens per session scan A b8a59b2522aa
final-local-product-review is a skill published in the GitHub repository ryne2010/harness-engineering-audit (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 136 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-05.
Other skills, from other repositories
debugging-diagnosis
Diagnose and fix bugs through reproduction, minimization, hypotheses, instrumentation, targeted fixes, and regression coverage. Use when the user reports failing behavior, a broken test, runtime error, flaky workflow, or asks for debugging before implementation.
test-first-implementation
Implement behavior with a red-green-refactor loop, observable tests, and small vertical slices. Use when the user asks for TDD, test-first work, regression-first fixes, or a feature that needs clear behavior before implementation.
debug
Systematic debugging when a failure's cause is unknown: reproduce first, isolate, fix the root cause once, prove it with a regression test. Use when a bug, crash, failing test or wrong output has no obvious cause, when a fix attempt did not work, or before claiming a stubborn bug fixed. For production incidents…
verify
Prove a change actually works before it counts as done. Use after building any non-trivial change, before deliver, and whenever claiming something works. Exercises real behavior end-to-end. Green tools alone are not verification.
layerkit-fix-from-dry-run
Fix failed integration verification from logs, tests, and docs evidence; edit real package files, no invention.
harness-engineering-playbook
Implement OpenAI Harness Engineering practices in any repository — AGENTS.md, PLANS.md, deterministic smoke/test/lint harness commands, strict architecture boundaries, observability from day 1, and entropy-control audits for reliable autonomous agent runs.