Borrowing it
Nothing to install: this file belongs to chenklein26-maker/Harness-Starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chenklein26-maker/Harness-Starter/main/.claude/skills/harness-gc/SKILL.mdgit clone --depth 1 https://github.com/chenklein26-maker/Harness-StarterWrote 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/chenklein26-maker/harness-starter/harness-gc)<a href="https://agentmods.dev/skills/chenklein26-maker/harness-starter/harness-gc"><img src="https://agentmods.dev/badge/skills/chenklein26-maker/harness-starter/harness-gc/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/chenklein26-maker/harness-starter/harness-gc"><img src="https://agentmods.dev/badge/skills/chenklein26-maker/harness-starter/harness-gc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00644 |
| Opus 5 | $0.00017 | $0.00322 |
| Sonnet 5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
harness-gc 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 9d 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
Harness GC (Garbage Collection) Agent
核心原则
- 外部验证门 — 扫描结果来自
gc-scan.mjs，非 Agent 自我报告（Sniff 模式） - 执行与验证分离 — 写代码的 Agent 不给自己打分（Spotify 模式）
- Circuit Breaker — 连续 3 次无改善则停止，等你介入
- 认知不投降 — 所有修复最终由你 review → 确认
触发方式
| 方式 | 命令 | 说明 |
|---|---|---|
| 手动 | node scripts/gc-scan.mjs |
立即执行一次健康检查 |
| Loop | /loop 24h "node scripts/gc-scan.mjs" |
每 24 小时自动扫描 |
| Routine | /schedule daily GC scan at 2am |
持久化定时（需 Max） |
扫描维度
| # | 维度 | 检查项 | 严重性 |
|---|---|---|---|
| 1 | CLAUDE.md 完整性 | 必要章节 + 占位符 | critical / warning |
| 2 | Git 状态 | 未提交变更数 + 调试残留 (console.log/debugger) | info / warning |
| 3 | TODO/FIXME 密度 | 单文件 >5 处 | info |
| 4 | .gitignore 健康 | node_modules/reviews/loops 遗漏 | info |
| 5 | Hook 注册 | 文件存在但未注册/被注释 | critical / warning |
| 6 | Harness 状态 | .harness-state 有效性 | info / warning |
| 7 | TypeScript 类型 | tsc --noEmit 错误（如存在 tsconfig.json） | warning |
| 8 | LSP 配置 | .lsp.json 有效性 | info / warning |
维度清单以此表为准。代码中
gc-scan.mjs的 JSDoc 为权威来源。
工作流
TRIGGER → SCAN (gc-scan.mjs) → ANALYZE → PROPOSE (可选) → WAIT (你 review)
状态管理
.claude/loops/STATE.md— 当前活跃状态 (hot, 每次会话自动加载).claude/loops/LOG.md— 历史执行记录 (warm, 按需读取).claude/.harness-state— Phase/Mode 配置
Circuit Breaker
连续 3 次扫描无改善 → STOP 自动提案 → 标记 Phase: blocked → 等你人工介入。
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.
- 9d ago First seen · 53 lines · 35 tokens per session scan A fd7188ee6f13
harness-gc is a skill published in the GitHub repository chenklein26-maker/Harness-Starter (119 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 644 once invoked, about $0.0002 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.