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 nek1987/auto-agent-harness --skill agent-evaluationgit clone --depth 1 https://github.com/nek1987/auto-agent-harnessWrote 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/nek1987/auto-agent-harness/agent-evaluation)<a href="https://agentmods.dev/skills/nek1987/auto-agent-harness/agent-evaluation"><img src="https://agentmods.dev/badge/skills/nek1987/auto-agent-harness/agent-evaluation/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/nek1987/auto-agent-harness/agent-evaluation"><img src="https://agentmods.dev/badge/skills/nek1987/auto-agent-harness/agent-evaluation.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 | $0.00032 | $0.12599 |
| Opus 5.5 | $0.00013 | $0.05040 |
| Sonnet 5.5 | $0.00006 | $0.02520 |
| Haiku 4.5 | $0.00003 | $0.01260 |
Grade A, and why
agent-evaluation 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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 · 1,711 lines · 32 tokens per session scan A 681e456d0050
agent-evaluation is a skill published in the GitHub repository nek1987/auto-agent-harness (4 stars, last pushed 6mo ago), with no licence file. It adds 32 tokens to every session and 12,599 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 2026-08-31.
Other skills, from other repositories
black-box-test
Use as an INDEPENDENT tester agent to test another agent's intesting ticket from the OUTSIDE — never your own, and never from the implementation diff. You test from the operational test contract + acceptance criteria only (never HOW it was built), writing one automated test per criterion that invokes the changed…
java-conventions
Use when a ticket adds or changes Java code and it must follow the repo's Java conventions — Effective Java, modern Java (records, sealed types, pattern matching, switch expressions), Optional discipline, immutability, try-with-resources, thread safety and virtual threads, Spring Boot constructor injection, and JUnit…
python-conventions
Use when a ticket adds or changes Python code and it must follow the repo's Python conventions — PEP 8, full type hints (PEP 484) checked by mypy/pyright, dataclasses, pythonic idioms, explicit error handling, asyncio and thread safety, ruff-clean, and pytest with coverage via the repo's env manager (uv/poetry).…
add-integration-test
Use when a ticket asks for integration or end-to-end coverage across components — an API route hitting a database, a service-to-service call, a multi-step flow, file or database persistence, concurrent writers, crash recovery — rather than a single unit. Invoke for "test the endpoint end to end", "cover the checkout…
record-evidence
Use after implementing a Dispatch ticket and running its checks, to produce and record acceptance-criterion evidence, then STOP. Invoke whenever you have finished and committed work on your claimed ticket and need to evidence each AC. Recording evidence is where your job ENDS — the runner (not you) records the…
contract-test
Use when a ticket changes the boundary between two components or services — an HTTP API and its client, a message producer and consumer, a public module interface — and both sides must keep agreeing. Invoke for "don't break the client", "add a contract test", a consumer-driven contract (Pact), schema validation…