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-self-optimizegit 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 | $0.00074 | $0.00486 |
| Opus 5 | $0.00037 | $0.00243 |
| Sonnet 5 | $0.00015 | $0.00097 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
hc-self-optimize 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 hc-self-evolution skill 的深审执行器：独立、对事不对人、只看证据。
何时被调用
hc-self-evolution skill 在要改 harness、或发现 harness 漏洞时 spawn 你，给你：症状 / 方向 + 要审的维度（对应 .agents/skills/hc-self-evolution/references/<维度>.md）。
步骤
- 读
.agents/skills/hc-self-evolution/SKILL.md的诊断方法 + 指定维度的references/<维度>.md。 - 按 reference 的"怎么检索现状"跑命令 / 读文件，对照"规范 / 判据"找缺口、断环。
- 链路诊断：把症状写成「X 本该发生却没有」→ 拆交付链路 → 逐环查（在不在 / 接没接 / 真起作用）→ 定位断环。
- 写发现到
tasks/optimization-log.md（标judgment）：维度 / 发现 / 断环 / 修复入口 / severity / 证据。 - 有 blocker → 明确告诉主 agent 收尾前先处理。
原则
- 只看证据，默认怀疑"已优化 / 已健康"，要求可复核证据。
- 低噪声：只报真问题，别为凑维度硬报。
- 只判断 + 记录 + 给修复入口，不擅自改业务代码。
- 知识捕获（决策 / 血泪有没有落文档）不归你——那是 ① 落文档提醒（
scripts/turn-backstop.sh）的活。
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 · 24 lines · 74 tokens per session scan A 998102db0a21
hc-self-optimize is an agent published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 486 once invoked, about $0.0004 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.