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/movebrickschi/harness-engineering-mcp/refactor-flownpx skills add movebrickschi/harness-engineering-mcp --skill refactor-flowgit clone --depth 1 https://github.com/movebrickschi/harness-engineering-mcpWrote 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/movebrickschi/harness-engineering-mcp/refactor-flow)<a href="https://agentmods.dev/skills/movebrickschi/harness-engineering-mcp/refactor-flow"><img src="https://agentmods.dev/badge/skills/movebrickschi/harness-engineering-mcp/refactor-flow.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 | $0.00098 | $0.01042 |
| Opus 5 | $0.00049 | $0.00521 |
| Sonnet 5 | $0.00020 | $0.00208 |
| Haiku 4.5 | $0.00010 | $0.00104 |
Grade A, and why
refactor-flow 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 3d 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-flow
适用场景
不改外部行为，只改内部结构（rename、提取函数、模块拆分、消除重复等）。
前置条件
确认 _playbook.md Part B.3 启动参数；额外 refactor_target（要重构的模块/文件/目录）。
流程步骤
阶段 0 · 上下文初始化
move_agent_to_root；建知识库目录（极简 META.md）。
阶段 1 · 现状评估
- 用
/health跑当前分数 - 用 explore subagent 列出待重构区域的：依赖入度 / 出度 / 测试覆盖率 / 已知 TODO/FIXME
- 输出
REFACTOR_BASELINE.md（行为基线 + 健康分基线）
阶段 2 · 测试网铺设
- 检查覆盖率：若未覆盖，先补足覆盖到 70%+
- commit：
test(scope): 补充重构前覆盖测试 - 这一步不通过不许进入阶段 3
阶段 3 · 重构方案 + 卡点
prompt: "测试网就绪，重构方案如下：[方案 A 一句话摘要]。请确认："
options:
- "方案 OK，分步执行"
- "需要修改方案（说明）"
- "暂不重构（关闭流程）"
阶段 4 · 分步原子 commit
每步：
- 改一小块 → 跑测试全绿 → commit
refactor(scope): 中文描述 - 任意一步测试不绿 → 立即 revert 该步，不允许"先红着提交后续修"
阶段 5 · 验证无行为变化
/qa（重点跑回归）/health分数应持平或上升/review
阶段 6 · 上线
/ship → /land-and-deploy → /canary（监控同模块错误率，确认与基线一致）。
阶段 7 · 复盘
append _lessons.md：重构动因 + 收益（健康分变化）+ 成本（工时）。
错误处理
- 覆盖率不达标且短期补不齐 → 退化为"小范围 PR + 大量手动验证"，明确告知用户风险
- 重构暴露隐藏 Bug → 暂停重构，先按
/bugfix-flow修复 + 上线，再回来继续 - 重构后健康分下降 → 不允许 ship，回阶段 4 检查
产物清单
META.md、REFACTOR_BASELINE.md、补测试 commit、若干原子重构 commit、/health 前后对比、PR 链接。
支持的修饰符
无。
与其他 skill 的关系
- 通常被
/dev-flow路由到（也可被用户直接触发） - 若过程中发现 Bug → 切换到
/bugfix-flow - 若实际目的是性能 → 切换到
/perf-flow - 自查：
/qa、/health、/review - 上线：
/ship、/land-and-deploy、/canary
附录
- 通用基座：见 _playbook.md Part B
- 文档模板：见 _playbook.md Part E
- 完整索引：见 _playbook.md Part F
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.
- 3d ago First seen · 101 lines · 98 tokens per session scan A 5c3810afda2a
refactor-flow is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 98 tokens to every session and 1,042 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 2026-08-31.
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…