Garbage Collection Agent — 定期扫描项目健康状态，检测文档/代码一致性漂移，自动发起修复提案。
$ npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-gc --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/harness-gc .claude/skills/harness-gc && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "harness-gc" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-gc into .claude/skills/harness-gc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gc", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-gcType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-gc --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/harness-gc .agents/skills/harness-gc && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-gc" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-gc into .agents/skills/harness-gc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gc", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-gc --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/harness-gc .cursor/skills/harness-gc && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-gc" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-gc into .cursor/skills/harness-gc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gc", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/k1ein-chen/Harness-Starter.git --path .claude/skills/harness-gc--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-gc --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/harness-gc .gemini/skills/harness-gc && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-gc" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-gc into .gemini/skills/harness-gc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gc", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install k1ein-chen/Harness-Starter harness-gcInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/harness-gc .github/skills/harness-gc && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-gc" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-gc into .github/skills/harness-gc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gc", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install k1ein-chen/Harness-Starter harness-gc --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/k1ein-chen/Harness-Starter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/harness-gc .opencode/skills/harness-gc && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-gc" agent skill from https://github.com/k1ein-chen/Harness-Starter/tree/main/.claude/skills/harness-gc into .opencode/skills/harness-gc/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-gc", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
harness-gcGarbage Collection Agent — 定期扫描项目健康状态，检测文档/代码一致性漂移，自动发起修复提案。
Harness Gc is an agent skill from k1ein-chen/Harness-Starter. Garbage Collection Agent — 定期扫描项目健康状态，检测文档/代码一致性漂移，自动发起修复提案。
Its SKILL.md is about 360 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: 一套成熟完善的开箱即用的 Claude Code Harness Engineering 模板。三层自动化（安全/感知/审查），集成 LSP、OpenSpec SDD 工作流和 AI 一键初始化。新项目和已有项目均可使用。 The licence is MIT.
4 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit c211c43. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
nodeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Harness Gc loads about 360 tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 144 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from k1ein-chen/Harness-Starter at commit c211c43, republished under its MIT licence (© k1ein-chen). 144 words, ~360 tokens.
.claude/skills/harness-gc/SKILL.md (or your agent's skills folder).gc-scan.mjs，非 Agent 自我报告（Sniff 模式）| 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） |
| # | 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。
TRIGGER → SCAN (gc-scan.mjs) → ANALYZE → PROPOSE (可选) → WAIT (你 review).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 配置连续 3 次扫描无改善 → STOP 自动提案 → 标记 Phase: blocked → 等你人工介入。
© k1ein-chen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/harness-gc of k1ein-chen/Harness-Starter.
Open the folder on GitHubat commit c211c43
Harness Gc next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Gc this skillk1ein-chen/Harness-Starter | 119 | — | ~360 | Automated safety check: Pass | MIT | |
| Garbage CollectionHabitat-Thinking/ai-literacy-superpowers | 114 | — | ~2.2k | Automated safety check: Pass | Custom licence | |
| Config Gcaffaan-m/ECC | 277k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Debugging Litert GPU Accuracygoogle-ai-edge/LiteRT | 3.5k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | |
| Alfworld Object Disposerzjunlp/SkillNet | 1.4k | — | ~341 | Automated safety check: Pass | MIT | |
| Alfworld Receptacle Searcherzjunlp/SkillNet | 1.4k | — | ~709 | Automated safety check: Pass | MIT |
Habitat-Thinking/ai-literacy-superpowers
This skill should be used when the user asks about "garbage collection rules", "entropy fighting", "documentation staleness", "dead code detection", "convention drift", "periodic checks", "auto-fix…
affaan-m/ECC
Garbage collection for your Claude Code configuration. An agent skill from affaan-m/ECC.
google-ai-edge/LiteRT
Diagnoses and fixes on-device GPU numerical corruption, garbage generation, zeroed KV caches, and ML Drift delegate lowering bugs for LiteRT and LiteRT-LM models on Android (OpenCL and WebGPU).
zjunlp/SkillNet
This skill disposes of an object by placing it into a disposal receptacle like a garbage can.
zjunlp/SkillNet
This skill searches for a specific receptacle (e.g., garbage can, cabinet) by systematically exploring the environment, checking multiple locations until found.
Xilinx/mlir-air
A skill your agent uses when an NPU kernel passes its standalone shape test but produces NaN, garbage, or stale values when invoked as part of a larger pipeline.
k1ein-chen/Harness-Starter
Initialize this project with the Harness Engineering starter template.
k1ein-chen/Harness-Starter
Entry point for new users — guides through initialization, architecture review, and cleanup.
k1ein-chen/Harness-Starter
将当前会话中的技术决策、运维流程或阶段性研发进展，归档为标准工程文档（ADR / SOP / Handover），并自动更新模块内的 README 归档索引。
k1ein-chen/Harness-Starter
Switch Harness workflow mode (full/hotfix/tweak) and development phase (design/build/fix).
k1ein-chen/Harness-Starter
Reviews technical decisions before implementation. An agent skill from k1ein-chen/Harness-Starter.
k1ein-chen/Harness-Starter
Independently verifies whether a completed task meets its defined goal conditions.
Garbage Collection Agent — 定期扫描项目健康状态，检测文档/代码一致性漂移，自动发起修复提案。. Harness Gc is an agent skill from k1ein-chen/Harness-Starter.
Run `npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a claude-code`. Or copy the skill folder (.claude/skills/harness-gc in k1ein-chen/Harness-Starter) into .claude/skills/harness-gc in your project. Claude Code loads it when a task matches its description.
Run `npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a codex`. Or copy the skill folder (.claude/skills/harness-gc in k1ein-chen/Harness-Starter) into .agents/skills/harness-gc in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add k1ein-chen/Harness-Starter --skill harness-gc -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-gc, .gemini/skills/harness-gc, .github/skills/harness-gc and .opencode/skills/harness-gc in your project.
Going by SKILL.md and its folder, Harness Gc needs the command-line tools its instructions call (node).
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Harness Gc is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 360 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Harness Gc: Garbage Collection (Habitat-Thinking/ai-literacy-superpowers, 114 stars), Config Gc (affaan-m/ECC, 277k stars), Debugging Litert GPU Accuracy (google-ai-edge/LiteRT, 3.5k stars) and Alfworld Object Disposer (zjunlp/SkillNet, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
k1ein-chen (a GitHub user) maintains it in k1ein-chen/Harness-Starter, which has 119 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 24, 2026.
Source: k1ein-chen/Harness-Starter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
