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/double-coding-lab/flow2spec/f2s-req-technpx skills add double-coding-lab/Flow2Spec --skill f2s-req-techgit clone --depth 1 https://github.com/double-coding-lab/Flow2SpecWhat 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 | $0.00045 | $0.02398 |
| Opus 5 | $0.00023 | $0.01199 |
| Sonnet 5 | $0.00009 | $0.00480 |
| Haiku 4.5 | $0.00005 | $0.00240 |
Grade A, and why
f2s-req-tech 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
执行口径:业务文档统一在
/.Knowledge/,本技能只产出.Knowledge/req-docs方案文档并参考.Knowledge内知识,不修改配置根rules/skills。
编排(主 / 子 agent)
- 两字段(
subAgent/switchAgentVerification)语义以统一入口为唯一事实源:Cursor/Claude 读配置根rules/f2s-flow2spec-unified-entry.*;Codex 读.codex/topics/f2s-flow2spec-unified-entry.md(与上同源,flow2spec init镜像)。本技能不复述。 - 拆子前提(硬约束):当
subAgent=true时,主 agent 必须先抽取一份「项目约定摘要」作为子 agent 的强制上下文,覆盖:对外契约规范、错误与返回约定、异步/集成规范、数据与存储约定、工程结构、模块边界,合计 < 80 行。若未做该前置,不拆子——验收返工成本 > 拆子收益,强行拆子得不偿失。 - 子职责:多源只读(
.Knowledge/topics、stock-docs、澄清后的req-docs、模版)+ 按.Knowledge/template/技术方案模版.md写req-docs方案初稿。 - 主职责:契约定稿、对照模版与澄清文档验收、处理交付单元/流程一致性。
- 校验:默认落盘侧自验;本技能不绑定交叉校验。
根据需求生成技术方案文档
用户在对话中提供已澄清的需求(或需求摘要、PRD 路径),并可选择附带需求条件(如范围限定、必须/禁止使用的技术、端侧限定、优先级等)。你需要基于业务知识文档(.Knowledge/)和当前 agent 已加载的 rules/skills,输出一份可直接用于实现的技术方案文档。
用途:本技能产出的技术方案供后续代码实现使用,开发按该文档实现功能。不限于后端,适用于后端、前端、全栈、移动端、脚本工具等任意场景。不用于生成 Rules/Skills。
结构范本:技术方案按 .Knowledge/template/技术方案模版.md 中的可选积木按需组装输出。不要硬套固定章节:只写本次实现真正需要的交付单元、数据结构、配置、依赖、流程或异常处理;每个交付单元小节内同时说明契约/输入输出与必要处理流程,避免再单独拆「接口及流程说明」「关联调用流程」「流程说明」等大章重复描述同一单元。
输入
- 第一参数(必填):澄清后的需求描述,或需求/PRD 文档路径(如
.Knowledge/req-docs/xxx.md、.Knowledge/stock-docs/需求_终稿.md)。 - 后续参数或用户补充(可选):需求条件与约束,例如:
- 范围(只做某模块、某端)
- 必须/禁止使用的技术栈、接口风格
- 与现有某模块的边界
- 性能、安全、合规要求
输出结构
生成文档时,先读取 .Knowledge/template/技术方案模版.md 作为结构参考,按需选用其中的章节积木;与需求无关的整节可省略,也可根据项目实际增加未列出的章节。
拆子前置(可选,仅当 subAgent=true)
主 agent 在拆子前,必须产出「项目约定摘要」作为子 agent 的强制输入,否则不拆子。摘要篇幅上限 < 80 行,必须包含以下 6 类条款(技术栈无关,按项目实际填具体值):
- 对外契约规范:接口 / 事件 / 消息 / 组件 / 脚本入口的命名、版本、鉴权、分页、通用返回字段等契约约定。
- 错误与返回约定:错误码体系来源、前缀 / 分段规则、必选字段(如 code / message / data)、状态分层。
- 异步 / 集成规范:消息队列 / 事件总线 / 定时任务 / 外部服务调用的命名、消费者组织、重试与幂等约定。
- 数据与存储约定:库 / 表 / 字段 / 缓存 / 文件 / 搜索等命名规范、主键 / 索引 / 时间字段约定、分库分表策略(若有)。
- 工程结构:模块分层(如 controller / service / dao / domain,或前端的 pages / components / hooks / store,或等价命名)与包路径 / 目录约定。
- 模块边界:本方案涉及的既有模块与其他模块的调用 / 数据边界。
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 · 83 lines · 45 tokens per session scan A e575ce309db7
f2s-req-tech is a skill published in the GitHub repository double-coding-lab/Flow2Spec (47 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 2,398 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…