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-flownpx skills add movebrickschi/harness-engineering-mcp --skill dev-flowgit 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 | $0.00219 | $0.03195 |
| Opus 5 | $0.00110 | $0.01597 |
| Sonnet 5 | $0.00044 | $0.00639 |
| Haiku 4.5 | $0.00022 | $0.00319 |
Grade A, and why
dev-flow 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 2d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-flow
本 skill 是开发组合拳的唯一入口路由器,自身不执行业务流程,只完成"问 → 写 dispatch-context.json → 指示主 agent 调用对应子 skill"。所有规范、卡点、文档模板 见单一事实源 _playbook.md。
适用场景
- 用户抛来一个开发任务,但你不确定该走哪个流程
- 用户口头说"接需求 / 开始开发 / 组合拳"
- 任务涉及前端、后端、全栈、bug 修复、重构、性能、第三方接入中的任意一项
前置条件
无强制前置;建议在进入路由前先确认:
~/Projects/_requirements/目录存在- 用户当前工作目录是项目根目录或可由
move_agent_to_root切换
决策树(路由器视图)
flowchart TD
start[用户任务] --> intent{识别 intent}
intent -->|bug/500/崩溃| bugfix[bugfix-flow]
intent -->|重构/整理| refac[refactor-flow]
intent -->|性能/慢| perf[perf-flow]
intent -->|接入/SDK| tp[third-party-flow]
intent -->|新功能| feat{有 PRD?}
feat -->|有 PRD| docFlow{开发范围}
feat -->|没 PRD| oneliner{开发范围}
feat -->|有原型项目| protoFlow{开发范围}
docFlow -->|前端| docFE[dev-flow-doc-fe]
docFlow -->|后端| docBE[dev-flow-doc-be]
docFlow -->|全栈| docFull[dev-flow-doc-full]
oneliner -->|前端| oneFE[dev-flow-oneliner-fe]
oneliner -->|后端| oneBE[dev-flow-oneliner-be]
oneliner -->|全栈| oneFull[dev-flow-oneliner-full]
protoFlow -->|前端| protoFE[dev-flow-proto-fe]
protoFlow -->|后端| protoBE[dev-flow-proto-be]
protoFlow -->|全栈| devFull[dev-flow-full]
oneFE & oneBE & oneFull --> upgrade{触发升级?}
upgrade -->|DB schema / 鉴权 / 支付 / >8h| forceDoc[强制升级 dev-flow-doc-*]
upgrade -->|否| keep[保留一句话流程]
升级触发条件(任一命中即强制 oneliner → doc):
| 信号 | 关键词 |
|---|---|
| DB schema | 数据库 / schema / 建表 / migration |
| 鉴权 / 多租户 | 鉴权 / 权限 / auth / 租户 |
| 支付 / 订单 / 钱包 | 支付 / 订单 / wallet |
| 估算 > 8h | "大改" / "跨多模块" |
注:本决策树即
harness_route_task工具的核心逻辑;该工具会同时返回efficiency_hints帮你选完后立刻知道下一步该怎么省 token。
流程步骤
步骤 1 · 收集启动参数(A.1)
使用 AskQuestion 一次性收集(如用户消息已提供则对应项跳过)。
问题 1 · 任务类型
prompt: "准备开始。请帮我快速定位任务类型:"
options:
- "新需求/新功能"
- "修 Bug"
- "重构/整理代码"
- "性能优化"
- "接入第三方服务"
若选了"新需求",追问 2-1 输入形式
prompt: "PM/用户给你的输入是什么形式?"
options:
- "完整需求文档(PRD、飞书文档等)"
- "PM 给了一个可运行的参考/原型项目"
- "一句话模糊需求(比如'加个筛选')"
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.
- 2d ago First seen · 263 lines · 219 tokens per session scan A a2ed7dbef3a3
dev-flow is a skill published in the GitHub repository movebrickschi/harness-engineering-mcp (2 stars, last pushed 3mo ago), licensed MIT. It adds 219 tokens to every session and 3,195 once invoked, about $0.0011 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.