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 skills/harness-base/harness-control/hc-self-evolutionnpx skills add harness-base/harness-control --skill hc-self-evolutiongit clone --depth 1 https://github.com/harness-base/harness-controlWrote 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-base/harness-control/hc-self-evolution)<a href="https://agentmods.dev/skills/harness-base/harness-control/hc-self-evolution"><img src="https://agentmods.dev/badge/skills/harness-base/harness-control/hc-self-evolution.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.01754 |
| Opus 5 | $0.00046 | $0.00877 |
| Sonnet 5 | $0.00018 | $0.00351 |
| Haiku 4.5 | $0.00009 | $0.00175 |
Grade A, and why
hc-self-evolution 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
自进化 / harness 规范检查(hc-self-evolution)
harness 不只治理被管工程,也要管自己。本 skill 是规范检查层:检查 harness 本身符不符合规范、有没有缺口/漏洞、该怎么改。
- 检查层 ≠ 操作层:
hc-add-rule/hc-prd/hc-dev/hc-git-workflow等是操作层——它们做事,是被检查对象 + 发现缺口后的修复工具,不作为审查逻辑被复用。 - 落文档提醒(每轮 capture)是另一套机制,不属本 skill。
何时用(两个触发)
- 要改 harness 某处(方向已定)→ 引导按结构改对、查连带影响。
- 发现 harness 漏洞 / 症状(如"某规则工作时没进上下文")→ 诊断是哪一环断了。
不用:纯被管工程开发任务、琐碎改动。
触发后、开始改之前:扫一眼 tasks/lessons.md 顶部最近 1-2 个月的条目(grep '^## 202' tasks/lessons.md | head -20 看标题),找跟本次要改领域同型的坑。反复出现 = 晋升成规则的信号(rule-0007),别又多记一条 lesson 就完事。
诊断方法(链路 / 不变量)
harness 每个能力是一条链路;漏洞 = 某环断了。
- 把症状写成「X 本该发生却没有」。
- 拆出交付 X 的链路(环节序列)。
- 逐环查:在不在 / 接没接 / 真起作用——机器能查的跑
*-audit、*-index --check;查不了的判断。 - 定位断环 → 读对应维度 reference 修 → 查有没有连带破坏别的环 → 记 lesson(反复出现晋升成规则)。
例:症状「某规则工作时没进上下文」→ 链路 定义(AGENTS.md) → 加载(CLAUDE.md @import/就近) → 选取(按任务挑相关) → 遵守 → 拦截 → 逐环发现「选取」环没有 task→规则 选择器 = 断点 → 修复走 references/rules.md。
维度索引(审到哪个读哪份;逐项过、不靠记忆)
每份 reference 给该维度的 规范 / 检索 / 判据 / 漏洞 / 修复:
references/skills.md— skill 体系references/rules.md— 规则references/docs.md— 文档(README / AGENTS / CLAUDE / context)references/eval.md— eval 题库 / 流程references/templates.md— 模板references/gates-hooks.md— verify / 护栏 / 门禁 / 触发(含 codex&claude 对等)references/decisions-context-features.md— 决策 / 上下文 索引区(features 区已退役,文件名保留旧称)references/sandbox.md— 被管工程本地验证环境references/subagents.md— 子 agent(.claude/agents/)references/lessons-memory.md— 错题本 / 记忆 / 晋升references/project-onboarding.md— 被管工程接入references/index-system.md— 索引体系(横切)references/process-coverage.md— 流程覆盖(任务类型→流程;缺口如 loop-engineering)
巡检/审查时先把总览索引当地图(默认不加载、自检时查):docs/rules/index.yaml、.agents/skills/README.md、各区 README.md/index.yaml、docs/decisions/index.yaml、docs/eval/index.yaml。
4 条 meta(强制)
- 全覆盖:维度逐项过,不许凭记忆只查一部分。
- 每项给方法:用对应 reference 的 检索 / 方向 / 规范边界,不空谈。
- 列表外:这些维度之外,是否要补新 harness 流程(如 loop-engineering playbook)。
- 自身(别漏):harness 进化后,本 skill 与 references 自己要不要改——维度有没有漏、references 过没过期、这套审查本身该不该调。
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/decisions-context-features.md 8.0 KB
- references/docs.md 9.2 KB
- references/eval.md 6.6 KB
- references/gates-hooks.md 12 KB
- references/index-system.md 10 KB
- references/lessons-memory.md 7.8 KB
- references/process-coverage.md 9.5 KB
- references/project-onboarding.md 6.2 KB
- references/rules.md 8.8 KB
- references/sandbox.md 6.6 KB
- references/skills.md 6.8 KB
- references/subagents.md 7.3 KB
- references/templates.md 6.2 KB
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.
- 5d ago First seen · 73 lines · 92 tokens per session scan A 37ff905d07e2
hc-self-evolution is a skill published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,754 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…