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 aAAaqwq/AGI-Super-Team --skill agi-super-team-orchestratorgit clone --depth 1 https://github.com/aAAaqwq/AGI-Super-TeamWrote 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/aaaaqwq/agi-super-team/agi-super-team-orchestrator)<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.
<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>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 | $0.00066 | $0.01274 |
| Opus 5.5 | $0.00026 | $0.00510 |
| Sonnet 5.5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00127 |
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.
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
- 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。
- 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。 - 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。
- 叶子和
ast-governor已被禁止使用 Agent 工具,不能继续委派。 - 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。 - 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。
- 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。
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.
- 21d ago First seen · 52 lines · 66 tokens per session scan A fb6479ad6433
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.
Other skills, from other repositories
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
aigon-board
Show Kanban board or list view.
aigon-next
Suggest the most likely next workflow action based on current context.
aigon-feature-prioritise
Prioritise feature - assigns ID, moves to backlog.
aigon-feature-reset
Reset feature - remove worktrees, branches, state, and return lifecycle to backlog.