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 harness-mini/harness-mini --skill evaluategit clone --depth 1 https://github.com/harness-mini/harness-miniWrote 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/harness-mini/harness-mini/evaluate)<a href="https://agentmods.dev/skills/harness-mini/harness-mini/evaluate"><img src="https://agentmods.dev/badge/skills/harness-mini/harness-mini/evaluate/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/harness-mini/harness-mini/evaluate"><img src="https://agentmods.dev/badge/skills/harness-mini/harness-mini/evaluate.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 | $0.00076 | $0.01002 |
| Opus 5.5 | $0.00030 | $0.00401 |
| Sonnet 5.5 | $0.00015 | $0.00200 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
evaluate 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are grading work against its plan's acceptance criteria — never against vague satisfaction. Agents confidently praise their own work; evaluation exists to break that.
Pick the tier (record it in the plan's eval: field)
"Always spawn an Opus evaluator" is too expensive for every change — if the default is too heavy, people bypass it, and then there is no firewall. So scale rigor with risk. Default is L1.
| Tier | Who grades | Use for | Cost |
|---|---|---|---|
| L0 | builder attaches evidence; main agent runs a compact checklist | tiny, low-risk changes whose criteria are 100% machine-checkable (docs, glue, a one-line fix) | ~free |
| L1 (default) | an independent lightweight reviewer — a fresh context (haiku sub-agent, or a separate prompt/thread on a CLI without sub-agents) | normal slices | low |
| L2 | the full evaluator agent (Opus / strongest available) | cross-slice work, architecture, security, data-loss risk, public-API changes, release gates | high |
When in doubt, go up a tier. L0 is only honest when no criterion needs judgment — the gate is the passing tests, not the builder's opinion. If a criterion needs a human/agent call, it is at least L1.
The firewall is the separate context, not the tooling. No sub-agents available? Run L1/L2 as a fresh prompt/thread with only the criteria + the diff (see
$HOME/.harness-mini/docs/codex-getting-started.md/$HOME/.harness-mini/docs/cursor-getting-started.md).
Procedure (every tier)
- Read the plan's acceptance criteria (from
to-prd). They are the contract. - Verify by interaction, not by reading. Run the tests. Run the app/endpoint where possible. A criterion passes only with evidence you produced — never the builder's claim. (At L0 the "evidence" is the attached test output the main agent re-runs and confirms.)
- For each criterion emit
PASS/FAIL+ the evidence + (on FAIL) the smallest concrete gap. - L1/L2: apply
clean-codeas a secondary lens — cite specific violations.
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.
- today Changed 83157c557305
- 4d ago Changed · +2 lines f029430f8e33
- 2mo ago First seen · 72 lines · 76 tokens per session scan A e8220eae51c2
evaluate is a skill published in the GitHub repository harness-mini/harness-mini (6 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,002 once invoked, about $0.0003 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.
evaluate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| evaluateharness-mini/harness-mini | Skill | 6 | today | MIT | A | 76 | Claude Code, Codex |
| thorough-pr-reviewluabagg/agent-skills | Skill | 3 | 10d ago | MIT | A | 73 | Claude Code, Codex |
| evaluator-review-contractredker56/auto-harness | Skill | 15 | 6mo ago | MIT | A | 30 | Claude Code |
| open-code-reviewalibaba/open-code-review | Skill | 50k | yesterday | Apache-2.0 | A | 98 | Cursor |
| agent-watchdogBuilderIO/skills | Skill | 4.6k | 4d ago | MIT | A | 115 | Claude Code, Codex |
| comet-verifyrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 32 | Claude Code, Codex |
| reviewvercel/eve | Skill | 5.8k | yesterday | Apache-2.0 | A | 31 | Claude Code, Codex |