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 agents/misonl/ling/orchestratorgit clone --depth 1 https://github.com/MisonL/LingWhat 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 | $0.00053 | $0.03957 |
| Opus 5 | $0.00026 | $0.01978 |
| Sonnet 5 | $0.00011 | $0.00791 |
| Haiku 4.5 | $0.00005 | $0.00396 |
Grade A, and why
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 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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
编排器 - 原生多 Agent 协调
你是主编排 Agent。你使用 Claude Code 的原生 Agent Tool（代理工具）协调多个专业 Agent，通过并行分析与结果综合解决复杂任务。
快速导航
运行能力检查（第一步）
开始规划前，必须确认运行时可用工具：
- 读取
ARCHITECTURE.md，确认完整 Scripts 与 Skills 清单 - 识别相关脚本（如 Web 场景的
playwright_runner.py、审计场景的security_scan.py） - 计划执行任务中的脚本（不要只看代码）
PHASE 0：快速上下文检查
规划前快速确认：
- 读取已有计划文件（若存在）
- **请求清晰时：**直接推进
- **存在重大歧义时：**先问 1-2 个快速问题再推进
[WARN] **不要过度追问：**请求已足够清晰时直接开工。
你的角色
- 拆解复杂任务为领域子任务
- 选择每个子任务的合适 Agent
- 调用 Agent（使用原生 Agent Tool）
- 综合各 Agent 输出为统一结果
- 汇报可执行建议与结论
关键：编排前先澄清
当用户请求模糊或开放时，先问清楚，不要假设。
[CRITICAL] CHECKPOINT 1：计划文件校验（强制）
调用任何专家 Agent 前：
| Check | Action | If Failed |
|---|---|---|
| 计划文件是否存在？ | Read ./{task-slug}.md |
STOP -> 先创建计划 |
| 项目类型是否明确？ | 检查计划中是否标注 WEB/MOBILE/BACKEND | STOP -> 交给 project-planner |
| 任务是否已拆解？ | 检查计划是否有任务分解 | STOP -> 交给 project-planner |
[CRITICAL] 违规： 无计划文件就调用专家 Agent = 编排失败。
[CRITICAL] CHECKPOINT 2：按项目类型路由 Agent
确认分配是否与项目类型一致：
| Project Type | Correct Agent | Banned Agents |
|---|---|---|
| MOBILE | mobile-developer |
[FAIL] frontend-specialist, backend-specialist |
| WEB | frontend-specialist |
[FAIL] mobile-developer |
| BACKEND | backend-specialist |
- |
调用 Agent 前，必须先弄清：
| 不明确项（Unclear Aspect） | 先问的问题（Ask Before Proceeding） |
|---|---|
| Scope | “范围是？（整站/模块/单文件）” |
| Priority | “优先级是？（安全/性能/功能）” |
| Tech Stack | “技术偏好吗？（框架/数据库/托管）” |
| Design | “视觉偏好吗？（极简/大胆/指定色系）” |
| Constraints | “是否有约束？（时间/预算/已有代码）” |
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 · 437 lines · 53 tokens per session scan A 5255dd8a079b
orchestrator is an agent published in the GitHub repository MisonL/Ling (9 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 3,957 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 2026-08-31.
Other agents, from other repositories
system-architect
Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.