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-proto-benpx skills add movebrickschi/harness-engineering-mcp --skill dev-flow-proto-begit 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-proto-be)<a href="https://agentmods.dev/skills/movebrickschi/harness-engineering-mcp/dev-flow-proto-be"><img src="https://agentmods.dev/badge/skills/movebrickschi/harness-engineering-mcp/dev-flow-proto-be.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 5.1 | $0.00120 | $0.01628 |
| Opus 5 | $0.00060 | $0.00814 |
| Sonnet 5 | $0.00024 | $0.00326 |
| Haiku 4.5 | $0.00012 | $0.00163 |
Grade A, and why
dev-flow-proto-be scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 完整链路 + curl/Postman 验证 How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-flow-proto-be
适用场景
- PM 提供参考项目 A（可运行）
- B 项目只做后端
- 前端由别人实现或已存在
前置条件
确认 _playbook.md Part B.3 启动参数；额外需要 prototype_path 与 prototype_url。
流程步骤
本 skill 是
/dev-flow-full的"后端裁剪版"。
阶段 0 · 上下文初始化
同 /dev-flow-full 阶段 0。
阶段 1 · A 项目探索（A 只读，强化网络抓取）
move_agent_to_root切到 A/freeze+SwitchMode→ plan- 用
cursor-ide-browser走查目标 URL，强化browser_network_requests抓完所有 API：- 每个接口的请求 headers / body / query
- 响应 status / body 样例
- 耗时与状态码分布
- 并行派发 2 个 explore subagent（跳过前端 subagent）：
- Task A：项目骨架（技术栈、目录、构建、运行环境）
- Task B：后端实现（路由定义、控制器、Service、数据库 Schema、迁移文件）
- 输出：
API_CONTRACT.md（从真实请求反推，附原始样例）DATA_MODEL.md（实体 / 字段 / 关系 / 枚举 / 校验）ENV_NOTES.md（A 的运行特征：mock 数据？真实环境？特殊配置？）
阶段 2 · 需求澄清（卡点 1）
按 _playbook.md Part B.2 卡点 1。
阶段 3 · B 项目勘察
move_agent_to_root切到 BSwitchMode→ agent- 并行 3 个 explore subagent（跳过前端横切）：
- 后端骨架
- 类似实体复用（CRUD 模板、DTO、Validator）
- 后端横切（鉴权、日志、参数校验、错误处理、事务、限流）
- 输出
PROJECT_CONVENTIONS.md+REUSE_AUDIT.md
阶段 4 · 方案设计（卡点 2）
git checkout -b feature/[feature]- 后端
IMPLEMENTATION_PLAN.md+IMPACT_ANALYSIS.md - 涉及 DB →
MIGRATION_PLAN.md（M4） /plan-eng-review→ 卡点 2
阶段 5 · 契约交付卡点
向前端 owner 交付 API_CONTRACT.md 后阻塞：
prompt: "API 契约（基于 A 项目反推）已送前端 owner，结果？"
options:
- "前端已 sign-off，进入实现"
- "前端提出修改（粘贴意见）"
- "前端暂不可用，继续推进（风险：后续可能返工）"
阶段 6 · 垂直切片（卡点 3）
- 实现一个最具代表性接口（通常"读列表"）
- 完整链路 + curl/Postman 验证
- 与 A 项目对应接口的响应做 diff，确认行为对齐
- 卡点 3
阶段 7 · 水平铺开
backend-agent：剩余接口test-agent：单测 + 集成测试
阶段 8 · 自查
/qa、/review、/cso必做- 对 A 项目的请求逐个 replay 到 B，确认响应一致
阶段 9 · PM 验收（卡点 4）
demo-package.md 必含 A 与 B 的接口响应对比。
阶段 10 · 上线
若 M4 → 迁移单独跑。/ship → /land-and-deploy → /canary。
阶段 11 · 复盘
append _lessons.md。
错误处理
- A 项目接口行为难以在 B 复现（依赖第三方）→ 补
ENV_NOTES.md，与 PM 商讨可接受的差异 browser_network_requests抓不到完整接口（隐藏接口/WebSocket）→ 询问用户提供.har文件或 PM 协助- A 与 B 数据库结构差异大 → 在
MIGRATION_PLAN.md给出迁移方案
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.
- 5d ago First seen · 141 lines · 120 tokens per session scan A 4f098fdddc13
dev-flow-proto-be is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 120 tokens to every session and 1,628 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
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…
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…