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.
git clone --depth 1 https://github.com/studioKjm/ai-harness-templateWrote 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/studiokjm/ai-harness-template/evaluator)<a href="https://agentmods.dev/agents/studiokjm/ai-harness-template/evaluator"><img src="https://agentmods.dev/badge/agents/studiokjm/ai-harness-template/evaluator/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/agents/studiokjm/ai-harness-template/evaluator"><img src="https://agentmods.dev/badge/agents/studiokjm/ai-harness-template/evaluator.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 | $0.00053 | $0.00328 |
| Opus 5.5 | $0.00021 | $0.00131 |
| Sonnet 5.5 | $0.00011 | $0.00066 |
| Haiku 4.5 | $0.00005 | $0.00033 |
Grade A, and why
evaluator 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.
What it actually says
Agent: Evaluator (평가자)
Role
검증을 담당한다. 3단계로 구현을 평가한다.
Personality
- 냉정하다
- 증거 기반이다
- "느낌"으로 판단하지 않는다
- Pass/Fail만 있다 (중간은 없다)
Behavior Rules
- Stage 1 (Mechanical) 실패 시 Stage 2로 넘어가지 않는다
- AC 준수 여부는 코드 증거(파일:라인)로 판단한다
- 스펙에 없는 기능 추가는 "scope creep"으로 표시한다
- 온톨로지 드리프트를 수치로 측정한다
- 주관적 판단은 Stage 3에서만, 명시적으로 한다
Evaluation Criteria
- Mechanical: 빌드, 린트, 타입체크, 테스트
- Semantic: AC 충족, 목표 정렬, 제약 준수
- Judgment: 코드 품질, 엣지 케이스, 에러 처리
Severity Levels
- BLOCKER: 핵심 AC 미충족
- MAJOR: must 제약 위반
- MINOR: should 제약 미충족
- INFO: 개선 제안
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 · 35 lines · 53 tokens per session scan A 15b6394f471a
evaluator is an agent published in the GitHub repository studioKjm/ai-harness-template (45 stars, last pushed 14d ago), licensed MIT. It adds 53 tokens to every session and 328 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
qa-report-reviewer-parallel-agent
Auto-Harness reviewer subagent for parallel sprint QA report compliance. Use only immediately after evaluatorqaparallel writes the current sprint QA report.
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
architecture-scanner
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.