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-kb-buildnpx skills add double-coding-lab/Flow2Spec --skill f2s-kb-buildgit 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 | $0.02346 |
| Opus 5 | $0.00023 | $0.01173 |
| Sonnet 5 | $0.00009 | $0.00469 |
| Haiku 4.5 | $0.00005 | $0.00235 |
Grade A, and why
f2s-kb-build 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
执行口径：本技能只维护
.Knowledge（topics/index/manifest-routing/matchers分片），不改配置根rules/skills。不再维护.Knowledge/manifest-matchers.json（已废弃聚合文件；flow2spec init会删除遗留副本）。
根据文档生成项目上下文（topics/index/路由清单）
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 SKILL 不复述。 - 首选分支（小变更 → 主全流程）：当本次改动 ≤ 2 个新 / 改主题，且 ≤ 1 个新 matcher，且无跨主题批量引用调整 时，全流程在主 agent 完成，不拆子。
- 中大变更分支（
subAgent=true且超出上述阈值）：- 主 agent 在主会话中列出文件级契约：子 A 只写
.Knowledge/topics/<foo>.md，子 B 只写.Knowledge/matchers/<m-foo>.json，路径互不重叠； - 子 agent 仅落盘契约内文件，不跨边界；
- 主 agent 单点编辑
.Knowledge/manifest-routing.json/.Knowledge/index.md（补taskToTopicRules、topicPaths、matcherPath、topicDependencies、topicMetadata）； - 主 agent 做整体验收。
- 主 agent 在主会话中列出文件级契约：子 A 只写
- 不推荐：单个子 agent 同时改 manifest / index / 多份 topics / matchers；以及「子 A 写、子 B 验」。
- 「一子写、主验」：仅在交付边界极窄（例如只产出 1 个新 matcher 分片草稿，manifest 引用仍由主写）时可接受。
- 写权硬约束：
.Knowledge/manifest-routing.json（含topicMetadata）/.Knowledge/index.md恒由主 agent 落盘，子 agent 不得触碰。 - 默认落盘侧 agent 自验；本 SKILL 不绑定交叉校验。
输入
- 接收一个参数：URL 或本地路径。
- 本地路径必须位于
.Knowledge/stock-docs/。 - 须为终稿：推荐文件名含
_终稿.md，或已由f2s-doc-final规范化；禁止以f2s-doc-arch产出的*_初稿.md作为入参直接执行本技能。 - 若入参路径含
_初稿、或用户刚完成架构初稿尚未执行f2s-doc-final：停止，回复须先执行f2s-doc-final <初稿路径>，待终稿落盘后再以终稿路径调用本技能。 - 若传入
.Knowledge/req-docs/，提示用户先整理为stock-docs终稿后再执行。
生成原则
- 拆解：文档较长或包含多块独立能力时，拆分为多个 topic；避免把无关能力塞到同一主题。
- 分工：
topics/：规则与流程正文（可执行知识）index.md：主题索引与语义说明（人读入口）manifest-routing.json+taskToTopicRules[].matcherPath指向的matchers/*.json：任务路由与关键词词表（机读入口）
步骤 1：获取文档内容
- URL：抓取正文；无法访问时提示用户先落地到
.Knowledge/stock-docs/*.md。 - 本地路径：读取 Markdown 文档，提炼主题与能力边界。
步骤 2：语义分析（必须）
从文档中提炼：
- 主题名与主题意图（可形成 topic id）
- 核心概念与关键流程
- 业务规则与边界条件
- 任务触发词（写入对应
matchers/<matcherId>.json的includeAny） - 与现有主题的依赖关系（用于
topicDependencies）
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 · 114 lines · 45 tokens per session scan A 46d8e16ecef1
f2s-kb-build is a skill published in the GitHub repository double-coding-lab/Flow2Spec (47 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 2,346 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.
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.