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-distillnpx skills add double-coding-lab/Flow2Spec --skill f2s-kb-distillgit clone --depth 1 https://github.com/double-coding-lab/Flow2SpecWrote 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/double-coding-lab/flow2spec/f2s-kb-distill)<a href="https://agentmods.dev/skills/double-coding-lab/flow2spec/f2s-kb-distill"><img src="https://agentmods.dev/badge/skills/double-coding-lab/flow2spec/f2s-kb-distill.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 | $0.00067 | $0.06051 |
| Opus 5 | $0.00034 | $0.03026 |
| Sonnet 5 | $0.00013 | $0.01210 |
| Haiku 4.5 | $0.00007 | $0.00605 |
Grade A, and why
f2s-kb-distill 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 today.
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 — 390 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，默认不改配置根rules/skills。
KB 自动合并协议（必须）
本技能不得把“人工执行命令”作为用户流程。用户触发本技能后，由 agent 自己完成知识候选生成、合并、构建与校验：
- 若本轮存在可沉淀知识，先在当前任务上下文中形成
kb-delta草稿，记录taskId、developerId、baseRevisions、changes与证据摘要；没有显式任务目录时可在内存中形成等价对象，不强制为了本技能创建.task。changes可使用appendBody/replaceBody/updateFrontmatter；确需新主题时使用createTopic，并可携带taskRule与matcher让路由一并接入。 - 写入
.Knowledge前，必须用flow2spec kb plan <delta>或等价内部能力预演；若 topic revision 不一致，停止自动写入，转入语义合并说明。 - 可自动合并时，由 agent 调用
flow2spec kb apply <delta>或等价内部能力写入 topic，并随后执行flow2spec kb build与flow2spec kb check。 - 用户只看到“知识库已同步 / 有语义冲突需确认 / 已跳过入库及原因”，不要求用户手动执行
kb plan/apply/build/check。
编排（主 / 子 agent）
subAgent/switchAgentVerification两字段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）。- 本技能默认不拆子：问答知识提取是单轮聚焦任务，由主 agent 全流程完成效率更高。
- 写权硬约束：
manifest-routing.json与.Knowledge/index.md恒由主 agent 单点落盘。 - 校验：落盘侧自验。
f2s-kb-distill：问答驱动的知识提取与入库
使用时机
- 用户提问 → agent 下钻源码回答 → 需要将发现的知识沉淀到 KB
- 通常由
f2s-kb-feedback-closing规则自动建议，也可用户主动调用 - 与
f2s-kb-sync区分：sync适合批量同步多个能力；distill专注单次问答的知识提取
输入
| 参数 | 必填 | 说明 |
|---|---|---|
| 用户问题 | 自动获取 | 上一轮用户的提问（自动从对话历史提取） |
| agent 回答 | 自动获取 | 上一轮 agent 的回答内容（自动从对话历史提取） |
| 命中主题 | 可选 | 如由 f2s-kb-feedback-closing 触发，会携带命中的 topicId |
| 下钻文件 | 自动分析 | 从回答中提取引用的文件/函数（自动分析） |
无有效问答上下文时中止并提示用户。
执行挡位（轻量 / 严格，agent 自动判）
f2s-kb-distill 只有一个入口（无 --fast 参数），进入流程第一件事是判挡：
判挡依据（4 个维度，全满足才走轻量挡）
| 维度 | 取值方式 | 走「轻量挡」的条件 |
|---|---|---|
上游 f2s-kb-feedback-closing case |
看本轮 / 上一轮 agent 回答末尾的收口块 | case 2 或 case 3（case 1 / 无收口 → 严格挡） |
| 本轮 Read 业务源码文件数 | agent 回顾本轮自己的工具调用 | ≤ 3 个 |
| 本轮回答引用的函数 / 类名数 | 数回答里反引号包裹的 xxx() / 类名 |
≤ 5 个 |
| 用户追问是否否定上游结论 | 看用户最新输入是否含"不对 / 重新分析 / 那条不准"等 | 否 |
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.
- today Changed · +2 lines ace8160be374
- 4d ago First seen · 388 lines · 67 tokens per session scan A 3e1d4c8f8eae
f2s-kb-distill is a skill published in the GitHub repository double-coding-lab/Flow2Spec (47 stars, last pushed today), licensed MIT. It adds 67 tokens to every session and 6,051 once invoked, about $0.0003 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…