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/dev-implementnpx skills add movebrickschi/harness-engineering-mcp --skill dev-implementgit clone --depth 1 https://github.com/movebrickschi/harness-engineering-mcpWhat 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 | $0.00118 | $0.01833 |
| Opus 5 | $0.00059 | $0.00916 |
| Sonnet 5 | $0.00024 | $0.00367 |
| Haiku 4.5 | $0.00012 | $0.00183 |
Grade A, and why
dev-implement 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Implement - 开发实现阶段
适用场景
完整开发流程的核心阶段。前置条件:
- 已通过
/dev-understand或手动方式生成~/Projects/_requirements/[feature]/的需求文档 - 目标项目 B 已确定
本阶段产出:实际代码 + 自查报告。
核心原则
- 先垂直切片再水平铺开:避免 3 个 subagent 同时朝错方向跑
- 复用优先于新建:必须先做复用审计
- 原子 commit:每子任务完成立即 commit,不要堆积
- 强制卡点:方案确认 + 切片确认 用
AskQuestion阻塞
启动参数收集
使用 AskQuestion 工具一次性收集:
- 需求名称(用于定位
~/Projects/_requirements/[feature]/) - 目标项目 B 路径
- 是否新建 git 分支(默认是,分支名
feature/[feature-name])
启动前必须验证:~/Projects/_requirements/[feature]/ 存在且包含 BUSINESS_FLOW.md / API_CONTRACT.md / DATA_MODEL.md。否则提示用户先跑 /dev-understand。
流程执行
前置:加载需求上下文
- 必读
~/Projects/_requirements/[feature]/下所有文档作为本次开发的输入 - 加载
~/Projects/_requirements/_lessons.md(如存在)作为经验背景 - 输出对需求的理解摘要,让用户快速校对
阶段 3:B 项目地形勘察 + 复用审计
move_agent_to_root切到 B 项目- 确保是 Agent 模式(如在 plan 模式则 SwitchMode 切回)
- 并行派 3 个 explore subagent:
- 项目骨架(栈/结构/构建启动/规范/git 工作流)
- 类似功能定位(项目里有没有类似实体?已有 CRUD 模板?字段命名习惯?)
- 横切关注点(鉴权/日志/校验/错误处理/测试约定)
- 输出
docs/PROJECT_CONVENTIONS.md(B 项目规范摘要) - 输出
docs/REUSE_AUDIT.md(复用审计),格式见~/.cursor/skills/dev-flow-full/templates/REUSE_AUDIT.md
阶段 4:方案设计 + 影响分析 ⏸ 卡点
- 创建 git 分支:
git checkout -b feature/[feature-name](如用户选择) - 输出
docs/IMPLEMENTATION_PLAN.md,包含:- A 概念到 B 实现的翻译映射表
- 新建文件清单(必做/应做/可选标注)
- 修改文件清单
- 数据库迁移方案(如需)
- 依赖检查(B 是否缺必要的库)
- 输出
docs/IMPACT_ANALYSIS.md:- 反向依赖链
- 回归风险点
- 建议回归测试范围
- 调用
/plan-eng-review评审方案 - 调用
AskQuestion阻塞等待:prompt: "方案设计完成。核心改动:[摘要]。请选择:" options: - "方案通过,进入切片验证" - "需要修改方案(请提供修改意见)" - "需要重新做复用审计"
阶段 5:垂直切片验证 ⏸ 卡点
- 选最具代表性的端到端场景(通常是核心 CRUD 中的"列表"或"读")
- 实现最小切片:1 个接口 + 1 个页面 + 1 个测试
- 手动跑通切片,验证:
- 技术栈假设正确
- 与现有代码协同无冲突
- 性能/规范符合 B 项目要求
- 切片代码独立 commit:
git commit -m "feat([scope]): 实现垂直切片验证" - 调用
AskQuestion阻塞等待:prompt: "垂直切片完成并通过验证。请选择:" options: - "切片 OK,水平铺开剩余功能" - "切片暴露问题,回方案设计阶段" - "需要先做更多切片验证"
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.
- yesterday First seen · 155 lines · 0 tokens per session scan A 606fe47e9d80
dev-implement is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 118 tokens to every session and 1,833 once invoked, about $0.0006 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…