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-doc-milestonenpx skills add double-coding-lab/Flow2Spec --skill f2s-doc-milestonegit 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 | $0.00092 | $0.03292 |
| Opus 5 | $0.00046 | $0.01646 |
| Sonnet 5 | $0.00018 | $0.00658 |
| Haiku 4.5 | $0.00009 | $0.00329 |
Grade A, and why
f2s-doc-milestone 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 — 149 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：读
.Knowledge/template/项目里程碑模版.md；落盘 仅.Knowledge/stock-docs/<范围名>里程碑.md（无第二路径参数）。
编排（固定，不受项目配置影响）
本技能不受 flow2spec.config.json 中 subAgent、switchAgentVerification（及旧键 subAgentVerification）影响：无论其为 true 或 false，一律按下述分工执行，禁止因配置改为「全主会话」或「子 agent 自验即结束」。
| 角色 | 步骤 | 职责 |
|---|---|---|
| 主 agent | 0、3、4 | 读模版与知识库主题索引、解析范围、派子、验证、必要时修订、回复用户 |
| 子 agent | 1、2 | 采集四源、套模版、Write 初稿 |
- 主 agent：步骤 0 → 下发「采集契约」→ 子 agent 步骤 1–2 落盘初稿。
- 主 agent：步骤 3 对照四源与「重要节点清单」验证（不全文重写；补缺、纠偏、「待确认」）→ 步骤 4 回复。
- 子 agent 禁止宣称「里程碑已验收完成」；终稿以主 agent 验证后为准。
步骤 0 仍
Read("flow2spec.config.json")（满足f2s-config-check前置），但不得用其中的subAgent/switchAgentVerification改变本技能编排。
子 agent 采集契约（主 agent 派子前写入 prompt）
| 字段 | 内容 |
|---|---|
scope |
用户语义范围一句 |
outputPath |
stock-docs/<范围名>里程碑.md |
sources |
见下文「四源」；须含知识库主题语义 |
template |
.Knowledge/template/项目里程碑模版.md（不写模版顶部说明 blockquote） |
delivery |
完整 Markdown，可直接 Write 至 outputPath |
stagePolicy |
见下文「阶段粒度」；契约中须复述一句 |
阶段粒度（必须，写入契约）
里程碑 Mx 仅记录功能/能力变更：当前仓库（或用户指定范围内）已落地或可核验的交付，例如模块/接口/数据模型/领域行为/知识库路由等，且须在四源中有依据。
不得单独占一行总览或独立 ## Mx · 的阶段类型（无四源交付支撑时禁止臆造；有交付也不得拆成「纯测试/纯联调」阶段）：
- 联调、集成测试、UAT、回归、验收、提测、上线检查（仅过程、无功能 diff）
- 仅环境/运维动作（执行 DDL、填配置、发版窗口、跨仓排期）且无本范围功能交付
- 以「稳定化 / 工程化 / 收尾」为名、实质仅为上述过程性工作的阶段
合并规则：同一次能力迭代内的工程性改动（如 id 类型对齐、分页格式、锁与并发）并入对应功能阶段正文，不另起「联调 / 测试 / 验收」阶段。
缺口处理：四源仅提及待联调、待验收、环境待补齐而无本范围功能交付 → 不写对应 Mx；可在 待确认 列一句，禁止用「计划项」填充总览表。
四源（采集与验证均须覆盖）
| 源 | 读什么 | 里程碑里怎么用 |
|---|---|---|
| req-docs | 范围内 .Knowledge/req-docs/*.md |
需求/方案节点、交付摘要 |
| git | git log --no-merges、git tag -l、package.json 版本 |
时间线、大版本/tag、提交锚点 |
.task |
todo.json、active/、completed/ 下 task.md 等 |
任务闭环、已交付步骤 |
| 知识库主题（语义） | 见下「主题索源」 | 与 index/manifest 已登记能力对齐，避免漏写「库里已有语义」的阶段 |
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 · 149 lines · 92 tokens per session scan A 61e2a915bb7f
f2s-doc-milestone is a skill published in the GitHub repository double-coding-lab/Flow2Spec (47 stars, last pushed 5d ago), licensed MIT. It adds 92 tokens to every session and 3,292 once invoked, about $0.0005 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.