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 lync-cyber/CataForge --skill start-orchestratorgit clone --depth 1 https://github.com/lync-cyber/CataForgeWrote 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/start-orchestrator)<a href="https://agentmods.dev/skills/lync-cyber/cataforge/start-orchestrator"><img src="https://agentmods.dev/badge/skills/lync-cyber/cataforge/start-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.01147 |
| Opus 5 | $0.00027 | $0.00574 |
| Sonnet 5 | $0.00011 | $0.00229 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
start-orchestrator 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 8d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
启动编排流程 (start-orchestrator)
能力边界
- 能做: 判断启动模式（新项目初始化 A / 已有项目恢复 B）、加载 orchestrator 角色定义、框架版本与 framework.json 检查、定位恢复阶段
- 不做: 通过 agent-dispatch 启动 orchestrator 子代理（见 §角色假设）；不替代 orchestrator 各 phase 的编排判定逻辑；不直接写 docs/ 子目录产物
角色假设（关键）
本 skill 在主线程会话执行，orchestrator 角色由主线程承载——读取 AGENT.md 加载角色定义后直接执行，不经 agent-dispatch 把 orchestrator 派为子代理（子代理无跨会话主线程状态，会断裂 §项目状态 写权限链路与进度定位）。
该约束是对调度行为的内部要求，非用户可见信息：首条回复不复述角色身份与调度宿主，直接进入对用户有意义的开场——分支 A 先确认对项目的理解再询问执行模式；分支 B 先报告恢复到的阶段与项目状态。
输入规范
- 必填: 项目描述自然语言字符串，或
continue关键字（触发分支 B 恢复模式） - 可选: {INSTRUCTION_FILE}（存在即触发分支 B）+
.cataforge/framework.json（版本检查依据）
输出规范
- 新项目: 触发 ORCHESTRATOR-BOOTSTRAP-PROTOCOLS §Project Bootstrap，产出 {INSTRUCTION_FILE} 初版并进入初始阶段
- 恢复推进: 不产出新文档，仅更新 {INSTRUCTION_FILE} §项目状态 块并继续推进当前阶段
- 本 skill 自身不写入 docs/ 任何子目录（实际文档产出由后续阶段 agent 完成）
Anti-Patterns
- 不通过 agent-dispatch 调度 orchestrator — 主线程直接扮演 orchestrator 角色；若误派为子代理，orchestrator 失去跨会话主线程状态感知，§项目状态 写权限链路断裂，恢复会话时无法定位进度
- 不跳过 §角色假设 直接进入步骤 — 角色声明是防止误用 agent-dispatch 的唯一显式约束
- 不在分支 B 跳过框架版本检查 — 版本占位符
0.0.0-template表示 scaffold 未初始化，直接恢复会让后续 agent 读到不一致状态 - 不在
.cataforge/framework.json缺失（框架尚未部署）时启动本 skill — 应先用 framework-update 同步包/scaffold 层再交接 start-orchestrator，否则跳过 scaffold 层同步
执行步骤
Step 1: 判断启动模式
- {INSTRUCTION_FILE} 不存在 → 分支 A（新项目）
- {INSTRUCTION_FILE} 存在 → 分支 B（已有项目）
分支 A: 新项目启动
- 读取 {AGENTS_SRC_DIR}/orchestrator/AGENT.md 的角色定义
- 执行
{AGENTS_SRC_DIR}/orchestrator/ORCHESTRATOR-BOOTSTRAP-PROTOCOLS.md§Project Bootstrap - 进入初始阶段（由执行模式决定，见 Bootstrap 末步「进入初始阶段」）
分支 B: 继续已有项目
B.1: 框架版本检查
- 读取
.cataforge/framework.json的version字段获取当前框架版本 - 如果
.cataforge/framework.json不存在或version为占位符（0.0.0-template）→ 提示用户: "未检测到框架版本信息，当前框架可能需要重新初始化。可运行cataforge setup或pip install --upgrade cataforge && cataforge upgrade apply修复。" - 版本检查仅提示，不阻断流程，继续 B.2
B.2: 恢复推进
- 读取 {AGENTS_SRC_DIR}/orchestrator/AGENT.md 的角色定义，执行其 §Startup Protocol 恢复推进（读状态 / 读索引 / 路由由该协议承担）
- 本入口独有分支:
- 当前阶段=completed → 提示项目已完成，询问用户意图(新版本/新需求/重新审查)
- 用户指定目标阶段（如"从架构设计开始"）→ 验证前置条件后跳转（前置条件见 orchestrator AGENT.md §Phase Routing，如上游文档须已 approved）
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.
- 8d ago First seen · 60 lines · 54 tokens per session scan A 30889dba1470
start-orchestrator is a skill published in the GitHub repository lync-cyber/CataForge (128 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 1,147 once invoked, about $0.0003 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.