agi-super-team-orchestrator

agi-super-team-orchestrator is a skill for Claude Code from aAAaqwq/AGI-Super-Team. It costs 66 tokens per session (1,274 once invoked), scanned A, original, MIT.

A coordinator for complex work that spans several kinds of expertise. It selects a small group of specialist agents, assigns bounded tasks, combines their evidence, and adds independent review when the decision is important.

In plain words
What is it for?
Use it for cross-functional or company-wide work, uncertain problems, parallel expert investigation, specialist review, or tasks that explicitly require coordinated agent collaboration.
Why use it?
It prevents every task from being sent to a large team and prevents delegated work from being mistaken for completed work. It also records limits, disagreements, evidence, owners, and actions that still need human approval.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Part of the agi-super-team-claudecode plugin — 1 skill, 14 agents shipped together

Good fit Use it for cross-functional or company-wide work, uncertain problems, parallel expert investigation, specialist review, or tasks that explicitly require coordinated agent collaboration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aaaaqwq/agi-super-team/agi-super-team-orchestrator
Install

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.

Any agent
npx skills add aAAaqwq/AGI-Super-Team --skill agi-super-team-orchestrator
Clone the repo
git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team

Made for: Claude Code.

Or install agi-super-team-claudecode, the plugin that ships this one along with the rest of its 1 skill, 14 agents.

Wrote 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.

agentmods badge for agi-super-team-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/agi-super-team-orchestrator/github.svg)](https://agentmods.dev/skills/aaaaqwq/agi-super-team/agi-super-team-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/agi-super-team-orchestrator"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/agi-super-team-orchestrator/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.

agentmods 80×15 button for agi-super-team-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/agi-super-team-orchestrator"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/agi-super-team-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,274 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00066 $0.01274
Opus 5.5 $0.00026 $0.00510
Sonnet 5.5 $0.00013 $0.00255
Haiku 4.5 $0.00007 $0.00127

Measured 21d ago against content hash fb6479ad6433, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agi-super-team-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 21d 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.

plugins/agi-super-team-claudecode/.claude/skills/agi-super-team-orchestrator/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGI Super Team|Claude Code 编排器

开始前先读取同一 Skill 根目录中的 ../orchestrate-agi-super-team/SKILL.md,并按需读取其 references。canonical Skill 决定是否组队、通用任务包、Governor 与人工批准契约;本 Skill 只定义 Claude Code 的运行时编排方式。

canonical 角色正文和专业 Skills 由安装器逐字复制;本文件不改写它们。

启动条件

  • 单领域、一步可完成的任务不组队,直接完成或调用一个最匹配的 Agent。
  • 跨职能、存在独立工作流、需要专业复核,或用户明确要求团队时启动。
  • 默认选择 2–3 个互补角色;只有能缩短关键路径时才并行。

Claude Code 调度协议

  1. 固定结果、成功标准、约束、非目标和必须由人类批准的现实动作。
  2. 使用 Claude Code 的 Agent 工具调用 ast-ceo 作为唯一协调者,并在任务中写明允许调用的直属 C-suite、输入、输出、边界和验收。
  3. CEO 只把边界清楚的工作交给匹配的 C-suite Manager;Manager 最多并行调用两个已安装的直属叶子。
  4. 叶子和 ast-governor 已被禁止使用 Agent 工具,不能继续委派。
  5. 重大结论、发布、资金、法律、安全或完成声明必须另行调用 ast-governor,向其提供原始声明和工作证据,不要求它迎合 CEO。
  6. 最终由主会话综合决定、证据、异议、限制、负责人和下一步。不得把委派成功当成任务完成。
  7. 如果当前 Claude Code 版本或权限不允许嵌套 Agent,主会话按同一路由平铺调用 Manager/叶子,并明确记录降级;不得伪称发生了嵌套委派。

Canonical Agent 路由

  • ast-cto(CTO (Jensen Huang)):需要技术战略选择、架构边界划分、接口/API 设计评审、技术选型对比、平台成本评估、系统可靠性设计或故障复盘时调用。
  • ast-pe(PE (Linus Torvalds)):已批准的设计需要跨模块实现、集成、测试、代码评审、缺陷修复或可回退交付时调用。
  • ast-cpo(CPO (Steve Jobs)):需要产品方向取舍、用户问题定义与需求澄清、体验与可访问性评审、优先级排序或可验证需求拆解时调用。
  • ast-cqo(CQO (Jim Simons)):需要量化假设设计、回测与复现、模型评估与独立复核、组合风险控制或实验预登记时调用。
  • ast-cmo(CMO (David Ogilvy)):需要市场定位与品牌策略、渠道增长实验、付费投放或 SEO 方案、获客测量与归因设计时调用。
  • ast-cfo(CFO (Warren Buffett)):需要预算与滚动预测、单位经济与定价证据、资本配置取舍、财务控制或成本优化时调用。
  • ast-cdo(CDO (Nate Silver)):需要数据契约与口径定义、数据质量与血缘治理、指标体系或分析模型设计、数据安全架构评审时调用。
  • ast-cco(CCO (MrBeast)):需要内容策略与编辑简报、平台内容适配、选题与脚本结构设计、内容制作编排或来源与权利审查时调用。
  • ast-clo(CLO (Alan Dershowitz)):需要合同与协议风险评审、隐私与跨境合规检查、许可与知识产权问题识别、监管政策适用判断时调用。
  • ast-cro(CRO (Richard Feynman)):需要研究问题设计、一手证据获取与核验、竞品或市场情报扫描、多源证据综合与不确定性说明时调用。
  • ast-cso(CSO (Michael Dell)):需要客户发现与资格审查、赢单策略、方案与投标叙事、销售管道分析或客户成功交接设计时调用。
  • ast-coo(COO (Andy Grove)):需要运营计划与执行节奏、责任与依赖映射、跨部门流程与 SOP 设计、产能规划或异常恢复安排时调用。
  • ast-governor(Governor):需要独立复核重大结论、发布、安全、资金、法律或完成声明,并给出放行门决定或风险升级时调用。

安全边界

  • 只调用本次安装产物中存在的 ast-* Agent;未安装的叶子不得作为可用能力声明。
  • 登录、凭证、付款、交易、发布、部署、生产写入、法律承诺、对外联系及不可逆动作必须取得人类明确批准。
  • 动态事实和高风险结论需要当前一手来源;没有运行证据统一标记为“待验证”。
  • Governor 保持独立;CEO 可以调整范围或接受剩余风险,但不得改写其证据结论。

Read the full file on GitHub · 52 lines

Changes

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.

  1. 21d ago First seen · 52 lines · 66 tokens per session scan A fb6479ad6433

Subscribe to this mod's changes

agi-super-team-orchestrator is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (105 stars, last pushed 10d ago), licensed MIT. It adds 66 tokens to every session and 1,274 once invoked, about $0.0003 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 2026-09-17.