Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lync-cyber/CataForgenpx agentmods add skills/lync-cyber/cataforge/workflow-framework-generatorWrote 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/lync-cyber/cataforge/workflow-framework-generator)<a href="https://agentmods.dev/skills/lync-cyber/cataforge/workflow-framework-generator"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/workflow-framework-generator/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/lync-cyber/cataforge/workflow-framework-generator"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/workflow-framework-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00097 | $0.03640 |
| Opus 5.5 | $0.00039 | $0.01456 |
| Sonnet 5.5 | $0.00019 | $0.00728 |
| Haiku 4.5 | $0.00010 | $0.00364 |
Grade A, and why
workflow-framework-generator 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 1mo 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
工作流框架生成器 (workflow-framework-generator)
能力边界
- 能做: 根据工作流类型+目标平台，生成完整的CataForge兼容框架（agents/skills/workflows/configs）
- 不做: 执行生成的工作流、替代领域专家做业务决策、硬编码特定工作流逻辑
输入规范
- 必填:
workflow_type工作流类型（自由文本，如"公众号写作"）+target_ide目标平台（枚举: claude-code | cursor | codex | opencode） - 可选:
multi_agent/tool_calls/structured_output/output_format/project_name/output_dir约束字段（详见 Phase 1.1） - 上游知识源:
references/domain-patterns.md（领域模式库）+references/platform-capabilities.md（平台能力矩阵）
输出规范
- 输出目录:
<output_dir>/（默认./generated-frameworks/<project_name>/） - 完整产出:
.cataforge/{framework.json, PROJECT-STATE.md, agents/, skills/, workflows/, hooks/hooks.yaml, rules/, platforms/, schemas/}+ 根目录README.md+docs/空目录 - 设计决策记录: 控制台输出 §设计决策输出 段定义的四节内容
- 不写入: 用户项目源码、CI 配置、运行时数据
执行流程
本 Skill 按三个阶段执行：解析 → 规划 → 生成。每个阶段有明确的输入输出契约。
Phase 1: 输入解析与需求澄清
1.1 解析用户输入
从用户消息中提取以下字段：
workflow_type: <string> # 工作流类型 (必填)
target_ide: <string> # 目标平台 (必填，枚举: claude-code | cursor | codex | opencode)
constraints:
multi_agent: <bool> # 是否需要多智能体协作 (默认: true)
tool_calls: <bool> # 是否需要工具调用 (默认: true)
structured_output: <bool> # 是否需要结构化产出 (默认: true)
output_format: <string> # 产出格式 (默认: markdown)
project_name: <string> # 项目名称 (可选，默认从 workflow_type 派生)
output_dir: <string> # 输出目录 (可选，默认: ./generated-frameworks/<project_name>)
1.2 输入验证
target_ide必须是已知平台之一。若用户输入模糊（如"vscode"），映射到最接近的平台并确认workflow_type为自由文本，但需确认其属于可识别的领域类别
1.3 需求澄清（条件触发）
当以下条件满足时，必须向用户提出澄清问题（每批 ≤ MAX_QUESTIONS_PER_BATCH）：
| 条件 | 澄清问题方向 |
|---|---|
| workflow_type 含糊（如仅"写作"） | 具体写作类型、目标平台/渠道、产出格式 |
| 领域不熟悉 | 核心业务流程、关键产出物、质量标准 |
| multi_agent 未指定 | 工作流复杂度是否需要多角色协作 |
| 涉及外部系统 | 需要集成的API/服务/数据源 |
澄清问题格式：
为了生成最适合的工作流框架，我需要确认以下信息：
1. [具体问题]
2. [具体问题]
3. [具体问题]
1.4 领域调研增强（条件触发）
当用户需求涉及你不熟悉的领域知识时：
- 读取
references/domain-patterns.md查找是否有匹配的领域模式 - 若无匹配，使用 web_search 检索该领域的标准工作流程和最佳实践
- 将调研结果结构化为：关键角色、核心流程、产出物清单、质量标准
- 将结构化结果融入后续的架构设计
What ships with it
21 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.
- examples/content-creation.yaml 4.6 KB
- examples/ecommerce-ops.yaml 3.9 KB
- examples/research-analysis.yaml 3.8 KB
- references/domain-patterns.md 9.2 KB
- references/platform-capabilities.md 2.9 KB
- scripts/__init__.py 0 B runs code
- scripts/scaffold.py 5.6 KB runs code
- scripts/validate_framework.py 16 KB runs code
- templates/agent.md.tmpl 872 B
- templates/common-rules.md.tmpl 1.8 KB
- templates/design-decisions.md.tmpl 542 B
- templates/framework.json.tmpl 804 B
- templates/hooks.yaml.tmpl 521 B
- templates/platform-profiles/claude-code.yaml.tmpl 1.2 KB
- templates/platform-profiles/codex.yaml.tmpl 1.8 KB
- templates/platform-profiles/cursor.yaml.tmpl 1.1 KB
- templates/platform-profiles/opencode.yaml.tmpl 1.1 KB
- templates/project-state.md.tmpl 738 B
- templates/skill.md.tmpl 600 B
- templates/sub-agent-protocols.md.tmpl 2.1 KB
- templates/workflow.yaml.tmpl 1.1 KB
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.
- 1mo ago First seen · 330 lines · 97 tokens per session scan A 11b9b70452e0
workflow-framework-generator is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session and 3,640 once invoked, about $0.0004 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…