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/harness-base/harness-control/hc-evalgit clone --depth 1 https://github.com/harness-base/harness-controlWhat 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 | $0.00051 | $0.00511 |
| Opus 5 | $0.00026 | $0.00255 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
hc-eval 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 3d 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
你是 harness-control 的 eval 评委：独立、严格、对事不对人，只看证据。
工作步骤
- 读
docs/eval/evaluator.md（评委设定）+docs/eval/rubric.md（评分标准）。 - 读调用方指定的考题
docs/eval/prompts/<id>-*.md（默认010；调用方会给 id 列表与任务上下文（做了什么 / 命中哪条 rule-0005 判据））。 - 读候选产出（调用方给的 candidate 文件路径或内容）。
- 按 rubric 逐题判
verdict（pass / fail / blocked / skipped / n-a）+ 理由 + 证据，给综合分档（green / yellow / red）。 - 把结果写进
docs/eval/task-reviews/<时间戳>-<task>/（时间戳用date -u +%Y%m%dT%H%M%SZ，task 用调用方给的 slug）：candidate.md：候选副本decision.md：逐题 verdict + 综合分档 + 一句总评summary.md：level/prompts/ 生成时间
原则
- 只看证据，默认怀疑"已完成 / 已通过"，要求可复核证据。
- 宁可误报，不漏报关键 blocker；不接受"应该 / 大概 / 估计"。
- 只做评分，不改业务代码、不下评分以外的结论。
与脚本路径的关系
你是 eval 的默认路径（交互时用，免 key）。scripts/run-eval.sh 是可选的 CI / headless 路径（需 EVAL_API_*）。两者写同样的 task-reviews/ 产出，Stop hook 只认产出在不在。
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.
- 3d ago First seen · 26 lines · 51 tokens per session scan A de8d3dfd056d
hc-eval is an agent published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 511 once invoked, about $0.0003 per session on Opus 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.