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 rules/double-coding-lab/flow2spec/f2s-intent-routinggit 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 | $0.01677 | $0.01677 |
| Opus 5 | $0.00839 | $0.00839 |
| Sonnet 5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00168 | $0.00168 |
Grade A, and why
f2s-intent-routing 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
f2s 意图识别路由
前置
执行本条前必须读 flow2spec.config.json：
intentRecognition: true→ 继续执行本条intentRecognition: false或字段不存在 → 跳过本条全部逻辑，不做任何自动调用
优先级
- 用户显式
$f2s-*命令最高优先级，按显式命令执行。 - 用户明确说「只讨论 / 先别改 / 不要执行 / 先评估 / 先聊方案」时，禁止自动调用 Skill。
- 当前已进入某个
f2s-*流程时，保持当前流程；不得自动切到其他流程，除非用户明确说「停止当前流程，改走 X」。 - 需求不完整禁自动进入撰写类技能：用户要求改代码但需求不完整时，优先
f2s-req-clarify，不得直接进入f2s-kb-feat/f2s-kb-fix；同理，用户要"出方案 / 生成技术方案"但需求含明显未决问题时，优先f2s-req-clarify，不得直接进入f2s-req-tech；用户要"拆任务 / 实现"但方案尚未落盘时，优先f2s-req-tech，不得直接进入f2s-req-plan/implement-tech-design。 - 过程编排型技能落盘后本轮不自动衔接下一技能（一处允许的单跳例外）：
f2s-req-clarify/f2s-req-tech/f2s-req-plan/f2s-doc-*完成落盘后，本轮默认只输出"文档已就绪 + 下一步指引"一行提示即停止；下一技能须由用户在新一轮明确触发再由本条分流。唯一允许的同轮单跳：f2s-req-clarify澄清文档落盘后直接自动衔接f2s-req-tech（详见skills/f2s-req-clarify/SKILL.md结束段），此后不得再跳；f2s-req-tech落盘后不得自动衔接f2s-req-plan/implement-tech-design。 - 用户只是在询问、比较、评估、解释时，不调用 Skill。
- 低置信度或多意图冲突时，先用一句话说明候选分流并反问，不调用 Skill。
意图 → Skill 映射
用户输入明确触发以下操作意图，且不违反上文优先级时，Agent 可直接进入对应 Skill，不需要等用户二次确认：
| 意图信号（示例） | 调用 Skill |
|---|---|
| 需求澄清、PRD 澄清、帮我理清需求、澄清一下 | f2s-req-clarify |
| 生成技术方案、出方案、技术设计 | f2s-req-tech |
| 提交代码、git commit、帮我提交、快捷提交 | f2s-git-commit |
| 新增能力、加功能、f2s-kb-feat | f2s-kb-feat |
| 修正实现规则、规则错了、f2s-kb-fix | f2s-kb-fix |
| 任务规划、创建任务 | f2s-req-plan |
| 知识库同步、全局同步、已实现能力同步 | f2s-kb-sync |
| 已有能力进知识库、多文件生成上下文 | f2s-kb-add |
| 新增规则、口述规则、把这条记到知识库 | f2s-kb-addRules |
| 生成项目上下文、终稿生成上下文 | f2s-kb-build |
| 合并上下文冲突、解决知识库冲突 | f2s-kb-merge |
| 删除项目上下文 | f2s-kb-rm |
| 知识库模板升级、知识库升级、一键升级迁移 | f2s-kb-upgrade |
| 项目架构说明、架构初稿 | f2s-doc-arch |
| 转成终稿模版、f2s-doc-final | f2s-doc-final |
| 生成项目里程碑、里程碑 | f2s-doc-milestone |
| PDF 转 MD | f2s-doc-pdf |
判断边界
调用：用户明确发起操作意图，且置信度高。
- "帮我做需求澄清" → 调用
f2s-req-clarify - "生成一份技术方案" → 调用
f2s-req-tech - "修复这个 bug，表现是 X，期望是 Y" → 调用
f2s-kb-fix - "新增这个配置开关，默认 false，影响范围是 X" → 调用
f2s-kb-feat
不调用：用户在询问或讨论，而非发起操作。
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 · 90 lines · 1,677 tokens per session scan A a55066ef881c
f2s-intent-routing is a cursor rule published in the GitHub repository double-coding-lab/Flow2Spec (47 stars, last pushed 4d ago), licensed MIT. It adds 1,677 tokens to every session, about $0.0084 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.