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-addrulesnpx skills add double-coding-lab/Flow2Spec --skill f2s-kb-addrulesgit 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 | $0.00075 | $0.03332 |
| Opus 5 | $0.00037 | $0.01666 |
| Sonnet 5 | $0.00015 | $0.00666 |
| Haiku 4.5 | $0.00007 | $0.00333 |
Grade A, and why
f2s-kb-addRules 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 3d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任务路径：凡
.task/落盘与续作，**必须以rules/f2s-task解析的TASK_ROOT为准（.task或.task/<developerId>；config → git → legacy）。下文若仍出现.task/todo.json/.task/active/，均视为TASK_ROOT/...的简写。
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，不动业务代码，不创建.task/（口述规则属于元配置变更，不是业务变更追踪）。
f2s-kb-addRules：用户口述规则进知识库
与既有技能的边界
- 与
f2s-kb-feat区分：f2s-kb-feat强绑「代码实现 + KB 同步」，命中changeTracking.feat会创建.task/；本技能只沉淀规则，不改代码、不追踪任务。 - 与
f2s-kb-build区分：f2s-kb-build输入是.Knowledge/stock-docs/<file>_终稿.md；本技能输入是用户当场口述的规则文本。 - 与
f2s-kb-add区分：f2s-kb-add输入是「多文件源码 / 配置」聚合到 stock-docs；本技能跳过 stock-docs，直接落 topic。
编排（主 / 子 agent）
subAgent/switchAgentVerification语义以统一入口为唯一事实源（Cursor/Claude 读rules/f2s-flow2spec-unified-entry.*；Codex 读.codex/topics/f2s-flow2spec-unified-entry.md）。本 SKILL 不复述。- 默认主 agent 全流程执行——口述规则单条短文，拆子收益低于 context 切换成本。
- 写权硬约束：
.Knowledge/manifest-routing.json/.Knowledge/index.md恒由主 agent 落盘。 - 落盘侧自验。
输入
- 一条或一段用户口述的规则文本（自由文本即可，无固定格式）。
- 用户不需要指定目标主题、文件名、
alwaysApply等参数；由本技能判定与提议。
强制前置：Read 创作侧准则
执行任何步骤前，须先 Read rules/f2s-topic-authoring.* 全文（Cursor/Claude：rules/f2s-topic-authoring.mdc；Codex：.codex/topics/f2s-topic-authoring.md），后续命名 / 骨架 / 依赖判定 / DAG 最小化 / 写盘权属均以该条为准。
步骤 1：意图归一
把用户口述文本归一为可落盘的"规则单元"：
- 抽取约束句式（"做 X 时必须 / 禁止 / 优先 Y"）或流程描述（"X 的处理顺序是 A→B→C"）；
- 标识规则适用场景（触发条件、文件路径范围、生命周期阶段等）；
- 不替用户引申、不补未说的边界——口述什么写什么，模糊处保留并在步骤 3 询问。
步骤 2：扫存量主题（必须）
- Read
.Knowledge/manifest-routing.json取topicPaths全集； - Read
.Knowledge/index.md主题表，按主题 id + 一句话意图扫一遍； - 必要时按规则正文中的关键词逐个 Read 候选
topics/<id>.md头部 10–30 行（不要全文加载所有 topic）； - 输出候选清单（重合度高 → 低，至多 3 个）作为步骤 3 的输入。
步骤 3：新建 vs 并入判定（必须，与用户确认）
向用户展示候选，按下列分支提议：
- 高重合（口述规则明显是某存量主题的细化 / 补充 / 例外）→ 提议「并入
topics/<existing>.md」，并指出拟插入位置（章节名 / 段落锚点）。 - 无重合 / 低重合（找不到合适宿主）→ 提议「新建
topics/<新 id>.md」；新 id 由本技能按规则正文生成 kebab-case，遵循f2s-topic-authoring命名约束（无版本后缀、无个人花名、与index.md既有标题不冲突）。 - 跨多个主题（一条口述同时约束 ≥2 个主题）→ 暂停，向用户呈现拆分选项：
- 选项 A：拆为 ≥2 条规则单元，分别并入对应主题；
- 选项 B：选主归并到一个主题，其它主题以一行交叉引用提示；
- 选项 C：新建一个总纲性主题统辖，旧主题加引用——仅在该规则确实横切多个领域时使用。
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.
- 3d ago First seen · 169 lines · 75 tokens per session scan A 37c7ce5979fb
f2s-kb-addRules is a skill published in the GitHub repository double-coding-lab/Flow2Spec (47 stars, last pushed 5d ago), licensed MIT. It adds 75 tokens to every session and 3,332 once invoked, about $0.0004 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.
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…