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 skills add chenshuai9101/agent-fde --skill skillsgit clone --depth 1 https://github.com/chenshuai9101/agent-fdeWrote 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/chenshuai9101/agent-fde/skills)<a href="https://agentmods.dev/skills/chenshuai9101/agent-fde/skills"><img src="https://agentmods.dev/badge/skills/chenshuai9101/agent-fde/skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chenshuai9101/agent-fde/skills"><img src="https://agentmods.dev/badge/skills/chenshuai9101/agent-fde/skills.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00628 |
| Opus 5 | $0.00000 | $0.00314 |
| Sonnet 5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
skills 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 10d 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.
What it actually says
SKILL: agent-fde — 用 FDE 方法论驱动一次企业 AI 落地
你是宿主 Agent（如 Claude）。agent-fde 的引擎不调用 LLM—— 语义分析由你完成，把结构化结果通过
fde_submit_analysis交给引擎校验并渲染交付物。 这就是"控制反转"：引擎管流程与交付物，你管分析与判断。
何时用
- 客户说"帮我们诊所做 AI 优化 / 帮公司搞自动化"
- 需要从需求分析 → 方案设计 → 原型 → 交付的结构化交付物（要文件，不要口头建议）
标准流程
- 查记忆：先
skill_find看是否有可复用的既往经验。 - 建项目：
fde_new(client_name, client_industry, project_name, client_input)→ 拿到engagement_id。 - 逐阶段分析并提交（每阶段先自己分析，再提交）：
- Phase 1 discovery →
fde_submit_analysis(phase="discovery", pain_points=[...]) - Phase 2 assessment →
fde_submit_analysis(phase="assessment", opportunities=[...]) - Phase 3 architecture →
fde_submit_analysis(phase="architecture", architecture={...}) - Phase 4 prototype →
fde_submit_analysis(phase="prototype", prototype_files=[...])， 然后用file_write把每个原型文件的真实代码写进引擎创建的prototype/骨架。 - Phase 5 handoff →
fde_submit_analysis(phase="handoff")
- Phase 1 discovery →
- 读交付物：
fde_deliverable(engagement_id, phase)拿 Markdown 发给客户。 - 结晶经验：Phase 5 完成后，
memory_crystallize把本次落地流程沉淀为可复用 Skill。
关键约束
- 阶段有序：必须 1→2→3→4→5。乱序会被引擎拒绝并告诉你
next_phase。 - 入参会被校验：pydantic 校验失败会返回结构化 errors，按提示修正后重试。
- 纯人工模式：若无需你分析，可用
fde_run_phase/fde_run_all走启发式模板（fallback）。 - 存储位置：engagement 在
~/.agent-fde/engagements/<id>/，交付物为0N-*.md。
各阶段方法论
见同目录下 phase1-discovery.md … phase5-handoff.md。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 36 lines · 0 tokens per session scan A 5bb3e06aa08e
skills is a skill published in the GitHub repository chenshuai9101/agent-fde (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 628 tokens. 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 2026-08-31.
Other skills, from other repositories
sofagent-fde
A Chinese-language deployment and knowledge-engineering process for mapping a company's work and turning its business rules into data and constraints for an AI system. It covers business workflows, possible AI tasks, relationships between concepts, and handover.
doris-debug-deployment
Use for Doris FE/BE startup failures, port conflicts, prioritynetworks misrouting, metadir corruption, and ADD/DROP BACKEND issues.
sofagent
A sofagent skill for FDEs—people who help businesses deploy AI—covering a four-stage diagnosis and the creation of a company-specific agent skill.
ci-cd-pipeline
Design and implement CI/CD pipelines for automated testing and deployment.
llm-deployment
Use when lLM deployment and serving — vLLM, Ollama, TGI, llama.cpp. Model quantization, GPU optimization, API serving. Use when working with llm deployment.
Inference
Guides model-serving and runtime-inference decisions across local, remote, and packaged deployment paths.