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-benpx skills add movebrickschi/harness-engineering-mcp --skill dev-flow-doc-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-doc-be)<a href="https://agentmods.dev/skills/movebrickschi/harness-engineering-mcp/dev-flow-doc-be"><img src="https://agentmods.dev/badge/skills/movebrickschi/harness-engineering-mcp/dev-flow-doc-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 | $0.00126 | $0.01616 |
| Opus 5 | $0.00063 | $0.00808 |
| Sonnet 5 | $0.00025 | $0.00323 |
| Haiku 4.5 | $0.00013 | $0.00162 |
Grade A, and why
dev-flow-doc-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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl / Postman 验证 → **卡点 3**（按 Part B.2） How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-flow-doc-be
适用场景
PRD 给定、前端由他人或 Mock 消费、只做 API / Service / DB。
前置条件
确认 _playbook.md Part B.3 启动参数；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
同 /dev-flow-doc-fe 阶段 0：move_agent_to_root → 建知识库目录 → 写 META.md → 加载 _lessons.md。
阶段 1 · 需求澄清（SwitchMode → plan）
通读 PRD，用 /office-hours 6 问视角挑战，追加追问：
- 并发策略（乐观锁 / 悲观锁 / 队列）
- 幂等设计（幂等键来源、有效期）
- 一致性要求（强一致 / 最终一致）
输出 questions-for-pm.md，按 _playbook.md Part B.2 卡点 1 阻塞。
阶段 2 · 契约先行（后端视角）
- 第一动作：输出
API_CONTRACT.md（入参 / 出参 / 错误码 / 分页 / 幂等键 / 鉴权） - 同步给前端 owner
契约交付卡点：
prompt: "API 契约已送前端 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 3 · 项目勘察（并行 3 个 explore subagent）
- Task A：后端骨架（技术栈、目录结构、构建启动、ORM、配置管理）→
PROJECT_CONVENTIONS.md - Task B：类似实体复用（CRUD 模板、DTO、Validator 在哪）→
REUSE_AUDIT.md - Task C：横切（鉴权、日志、参数校验、错误处理、事务、限流、监控）→ 并入
PROJECT_CONVENTIONS.md
阶段 4 · 方案设计
IMPLEMENTATION_PLAN.md：路由 / 控制器 / Service / Repo / DTO / SchemaIMPACT_ANALYSIS.md（模板见 _playbook.md Part E.7）：反向依赖链、回归范围- 如涉及 DB → 附
MIGRATION_PLAN.md（M4，模板见 Part E.9） /plan-eng-review→ 卡点 2（按 Part B.2）
阶段 5 · 垂直切片
- 挑选"读列表"或"读详情"接口
- 完整链路：路由 → 鉴权 → Service → Repo → DTO → 集成测试
- curl / Postman 验证 → 卡点 3（按 Part B.2）
阶段 6 · 水平铺开
backend-agent：剩余接口test-agent：单测 + 集成测试，覆盖IMPACT_ANALYSIS.md所列回归点- 每接口完成立即原子 commit（
feat(scope): 中文描述）
阶段 7 · 自查
/qa（接口层为主）/review/cso（权限 / 敏感数据 / admin 接口必做）- 汇总
self-check-report.md
阶段 8 · PM 验收
demo-package.md 用 curl/Postman 例子展示，卡点 4（按 Part B.2）。
阶段 9 · 上线
- 若叠加 M4 →
/land-and-deploy前单独跑迁移，确认成功再发代码 /ship→/land-and-deploy→/canary（重点监控 DB 慢查询与同类错误）
阶段 10 · 复盘
append _lessons.md，更新 META.md。
错误处理
- 契约被前端打回 → 回阶段 2 更新
API_CONTRACT.md - 切片卡在横切（鉴权 / 事务）→ 回阶段 3 补充
PROJECT_CONVENTIONS.md后再切 - 迁移脚本 up/down 不幂等 → 必须修到幂等才能进阶段 6
/cso暴露密钥/SQL 注入 → 立刻回阶段 6 修复
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 · 127 lines · 126 tokens per session scan A dac8e0d765ac
dev-flow-doc-be is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 126 tokens to every session and 1,616 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.
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…