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-featnpx skills add double-coding-lab/Flow2Spec --skill f2s-kb-featgit 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-feat)<a href="https://agentmods.dev/skills/double-coding-lab/flow2spec/f2s-kb-feat"><img src="https://agentmods.dev/badge/skills/double-coding-lab/flow2spec/f2s-kb-feat.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 | $0.00039 | $0.02420 |
| Opus 5 | $0.00019 | $0.01210 |
| Sonnet 5 | $0.00008 | $0.00484 |
| Haiku 4.5 | $0.00004 | $0.00242 |
Grade A, and why
f2s-kb-feat 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 4d 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 — 116 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：
f2s-kb-feat默认同步.Knowledge，无需用户额外提出"请同步知识库"。
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。代码实现完成或确认已有实现后，由 agent 自己完成知识候选生成、合并、构建与校验：
- 将本次能力变更转换为
kb-delta草稿，记录taskId、developerId、baseRevisions、changes与实现证据；若changeTracking.feat=true且已有任务目录，可把 delta 落在当前TASK_ROOT/active/<task-name>/kb-delta.json，否则可在内存中形成等价对象。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“能力与知识库已同步 / 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与switchAgentVerification的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）。本处不复述。- 代码子包（新增 / 修改实现代码）：
subAgent=true时可外包给子 agent 执行。 - 文档子包（rules / skills / topics / stock-docs 文风类改动）：默认不拆，由主 agent 写，以保证「现行真值覆盖 / 篇幅上限 / 禁历史否定堆砌」等文风合规。
- 若确需外包文档改动：子侧只输出「原位替换 diff」（before / after 小段），不得整文件重写；主合并落盘。
- 写权硬约束：
manifest-routing.json/.Knowledge/index.md恒由主 agent 落盘，子 agent 不得触碰。 - 落盘侧自验。
/新增能力（f2s-kb-feat）
输入
- 用户描述新增能力、场景、边界、可选路径。
步骤
步骤 0：变更追踪（仅当 changeTracking.feat: true）
执行前读取 flow2spec.config.json，若 changeTracking.feat: true：
- 检查
.task/todo.json是否存在活跃任务，将用户描述与keywords匹配。 - 命中 → 加载对应
task.md，展示剩余清单，在已有任务中继续。 - 无命中 → 创建新任务（见
f2s-task规则），将步骤 1–4 写入task.md作为任务 checklist。 - 执中必写盘：每完成
task.md中一步，同一会话内立即Edit将该步[ ]→[x]；禁止把打钩积压到「收尾/归档」一步、禁止口头完成代替写盘（见f2s-task「中断与会话结束」「归档门禁」）。 - 用户代办：凡须用户改库、配环境、点平台等项，同会话内追加写入
.task/active/<task-name>/user-todos.md（见f2s-task）；新建任务时若尚无代办，仍应创建该文件（可占位）。
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.
- 4d ago First seen · 116 lines · 39 tokens per session scan A 40a40f19b3e5
f2s-kb-feat is a skill published in the GitHub repository double-coding-lab/Flow2Spec (47 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 2,420 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.
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…