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 commands/joe-rq/harness-lab/refactorgit clone --depth 1 https://github.com/Joe-rq/harness-labWrote 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/commands/joe-rq/harness-lab/refactor)<a href="https://agentmods.dev/commands/joe-rq/harness-lab/refactor"><img src="https://agentmods.dev/badge/commands/joe-rq/harness-lab/refactor.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 | $0.00023 | $0.00562 |
| Opus 5 | $0.00012 | $0.00281 |
| Sonnet 5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
refactor 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 4d 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
/refactor
目标
引导用户创建 refactor 型 REQ。
前置检查
- 确认
requirements/目录存在。不存在 → 提示先运行/harness-setup - 确认
package.json中有req:create脚本。不存在 → 提示先运行/harness-setup - 确认当前无活跃 REQ（
requirements/INDEX.md中## 当前活跃 REQ下为"无"）。有活跃 REQ → 提示先完成或搁置当前 REQ
执行步骤
Step 1: 收集重构信息
使用 AskUserQuestion 询问：
- 重构目标（必填）：要重构什么？如"将 session 管理从中间件抽取为独立模块"
- 当前问题（必填）：为什么需要重构？如"session 逻辑散布在 5 个文件中"
- 为什么现在做（可选）：触发原因
Step 2: 创建 refactor REQ
运行：
npm run req:create -- --title "refactor: [重构目标]" --type refactor
Step 3: 补充重构详情
用 Edit 将 REQ 中的占位符替换为用户提供的实际信息：
[请描述技术债或流程缺口]（背景-当前问题）→ 用户的当前问题[请描述触发原因]（背景-为什么现在做）→ 用户的触发原因[模块/流程]（目标-重构）→ 用户的重构目标
Step 4: 提示用户确认
重点提醒：
- 确认"非目标"中的"不做功能行为变更"是否符合预期
- 如果涉及文件数 ≥4，考虑是否拆分 REQ
- 补充"颗粒度自检"
- 确认后运行
npm run req:start -- --id {reqId} --phase implementation
输出
- 创建的 REQ ID 和文件路径
- REQ 类型：refactor
- 已预填充：技术债描述占位、行为不变约束、skip-design-validation
- 核心约束提醒：重构后所有测试必须通过，行为不能变
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.
- 4d ago First seen · 57 lines · 23 tokens per session scan A bdc4f6d6f1cc
refactor is a command published in the GitHub repository Joe-rq/harness-lab (20 stars, last pushed 22d ago), licensed MIT. It adds 23 tokens to every session and 562 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.