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 5.5 | $0.00014 | $0.00258 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 4mo ago), licensed MIT. It adds 35 tokens to every session and 644 once invoked, about $0.0001 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.
harness-gc compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| harness-gcchenklein26-maker/Harness-Starter | Skill | 119 | 4mo ago | MIT | A | 35 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |