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-fullnpx skills add movebrickschi/harness-engineering-mcp --skill dev-flow-doc-fullgit 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-full)<a href="https://agentmods.dev/skills/movebrickschi/harness-engineering-mcp/dev-flow-doc-full"><img src="https://agentmods.dev/badge/skills/movebrickschi/harness-engineering-mcp/dev-flow-doc-full.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 | $0.00115 | $0.01455 |
| Opus 5 | $0.00057 | $0.00727 |
| Sonnet 5 | $0.00023 | $0.00291 |
| Haiku 4.5 | $0.00012 | $0.00145 |
Grade A, and why
dev-flow-doc-full 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-flow-doc-full
适用场景
PRD 给定，前后端都自己做，承担端到端交付责任。
前置条件
确认 _playbook.md Part B.3 启动参数；额外确认是否有独立前后端仓库或 monorepo（target_project 可能是 2 个目录）。
流程步骤
阶段 0 · 上下文初始化
同 /dev-flow-doc-fe 阶段 0，注意 target_project 可能是 2 个目录（前端 + 后端），分别 move_agent_to_root 时记录。
阶段 1 · 需求澄清（SwitchMode → plan）
通读 PRD，/office-hours 6 问视角挑战。输出 questions-for-pm.md，卡点 1（按 _playbook.md Part B.2）阻塞。
阶段 2 · 契约自治
- 自写第一版
API_CONTRACT.md AskQuestion让用户/PM 确认 2–3 个关键字段的业务含义- 此版本作为前后端实现的共同锚点，后续改动必须在此文档上同步
阶段 3 · 双侧勘察（并行 3 个 explore subagent）
- Task A：前端骨架 + 复用
- Task B：后端骨架 + 复用
- Task C：全栈横切（鉴权、日志、监控、错误处理）
输出 PROJECT_CONVENTIONS.md + REUSE_AUDIT.md（可分前后端两节）。
阶段 4 · 方案设计（Plan 模式）
IMPLEMENTATION_PLAN.md必须含前后端交互时序图（mermaid）- 如涉及 DB →
MIGRATION_PLAN.md /plan-eng-review→ 卡点 2（按 Part B.2）
阶段 5 · 端到端垂直切片（最关键）
- 1 个接口 + 1 个页面，真实 HTTP 调用，禁止 mock
- 跑通整条链路（前端按钮 → API → DB → 返回 → 前端显示）
- 原子 commit：
feat(scope): 实现端到端垂直切片 - 卡点 3（按 Part B.2）
阶段 6 · 水平铺开（同一消息并行派发三路）
backend-agent：剩余接口frontend-agent：剩余页面test-agent：单测 + 集成 + E2E- 每实现一个接口立即对应前端接入 + 手动自测
阶段 7 · 自查
/qa（E2E 全链路）/review/cso（权限 / admin 必做）/design-review（有 UI 必做）- 汇总
self-check-report.md
阶段 8 · PM 验收
demo-package.md 配 GIF/录屏，卡点 4（按 Part B.2）。
阶段 9 · 上线
/ship → /land-and-deploy → /canary。若叠加 M4，迁移单独跑。
阶段 10 · 复盘
append _lessons.md，更新 META.md。
错误处理
- 切片暴露契约字段不够用 → 立刻更新
API_CONTRACT.md，同步前后端改动 - 前后端在阶段 6 出现认知不一致 → 回阶段 2 回溯契约
- E2E 反复失败 → 回阶段 5 重新切片
- 阶段 6 任一 subagent 失败 → 暂停其他派发，先解决当前问题
产物清单
/dev-flow-doc-fe + /dev-flow-doc-be 产物并集 + 前后端交互时序图。
支持的修饰符
- M1 带设计稿 → 阶段 1 后
/plan-design-review，阶段 4DESIGN_TOKENS.md，阶段 7 必做/design-review - M2 无设计稿 UI → 新项目阶段 0 加
/design-consultation；已有项目阶段 4 后/design-shotgun - M3 新旧项目 → 同
/dev-flow-doc-fe/-be - M4 数据库迁移 → 阶段 4
MIGRATION_PLAN.md；阶段 5 本地 up→down→up；阶段 7/cso必做；阶段 9 迁移单独跑
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 · 117 lines · 115 tokens per session scan A d1c0cda7517d
dev-flow-doc-full is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 115 tokens to every session and 1,455 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…