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-flow-doc-fenpx skills add movebrickschi/harness-engineering-mcp --skill dev-flow-doc-fegit 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/dev-flow-doc-fe)<a href="https://agentmods.dev/skills/movebrickschi/harness-engineering-mcp/dev-flow-doc-fe"><img src="https://agentmods.dev/badge/skills/movebrickschi/harness-engineering-mcp/dev-flow-doc-fe.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 | $0.00125 | $0.01947 |
| Opus 5 | $0.00063 | $0.00974 |
| Sonnet 5 | $0.00025 | $0.00389 |
| Haiku 4.5 | $0.00013 | $0.00195 |
Grade A, and why
dev-flow-doc-fe 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-flow-doc-fe
适用场景
- 已有 PRD / 飞书文档 / Notion 文档，业务规则基本明确
- 后端接口已存在（或由别人并行开发）
- 本次任务只改前端代码
前置条件
确认 _playbook.md Part B.3 启动参数（feature_name、target_project、prd_path 必填）；如缺失，用 AskQuestion 补齐。
通常由父 skill /dev-flow 通过 dispatch-context.json 传入。
流程步骤
阶段 0 · 上下文初始化
move_agent_to_root进前端项目- 创建
~/Projects/_requirements/[feature]/，写META.md（模板见 _playbook.md Part E.1） - 加载
_lessons.md背景 - 复制/链接 PRD 到
PRD.md
阶段 1 · 需求澄清（SwitchMode → plan）
- 通读 PRD，用
/office-hours的 6 问视角挑战（模糊规则 / 边界 / 错误 / 权限 / 并发 / 空状态） - 输出
questions-for-pm.md（模板见 _playbook.md Part E.2） - 卡点 1（_playbook.md Part B.2）：
prompt: "需求文档/澄清已生成，请看 questions-for-pm.md。请选择："
options:
- "已和 PM 沟通，提供答复（粘贴在下条消息）"
- "需求清楚无疑问，进入下一阶段"
- "需要重新探索原型/项目某些细节"
收到答复后追加到 pm-answers.md，循环到无疑问。
阶段 2 · 契约对齐
- 与后端 owner 对齐
API_CONTRACT.md（字段、错误码、分页、幂等、鉴权） - PRD 没写的一律落纸，
AskQuestion让用户/后端 owner 确认关键字段
阶段 3 · 项目勘察（并行 2 个 explore subagent）
- Task A：前端骨架（技术栈、目录结构、构建、路由、状态管理、UI 库）→ 写入
PROJECT_CONVENTIONS.md - Task B：类似功能复用审计 → 写入
REUSE_AUDIT.md（模板见 _playbook.md Part E.6）
阶段 4 · 方案设计（Plan 模式）
git checkout -b feature/[feature]- 输出
IMPLEMENTATION_PLAN.md（模板见 _playbook.md Part E.5）：页面拆分、组件树、状态、路由、API 层 /plan-eng-review评审- 卡点 2：
prompt: "方案设计完成。核心改动：[一句话摘要]。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（SwitchMode → agent）
- 挑选代表性页面（通常"列表"或"详情"）
- 1 页面 + 1 接口对接 + 1 组件测试
- 原子 commit：
feat(scope): 实现垂直切片验证 - 卡点 3：
prompt: "垂直切片完成并通过验证。切片范围：[一句话]。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（说明哪些）"
阶段 6 · 水平铺开（并行 Task）
frontend-agent：实现剩余页面test-agent：交互 / 表单 / 路由测试- 每块完成立即原子 commit（
feat(scope): 中文描述）
阶段 7 · 自查
/qa（必做）/review（必做）/design-review（若有 UI 改动必做，修饰符 M1/M2 下更严格）- 汇总
self-check-report.md
阶段 8 · PM 验收
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 · 157 lines · 125 tokens per session scan A 4e1320c4c0b7
dev-flow-doc-fe is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 125 tokens to every session and 1,947 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.
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…