Agent Builder
shareAI-lab/learn-claude-code
Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.
多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属模型时使用。
Install Agent Team Manager
$ npx skills add countbot-ai/CountBot --skill agent-team-manager -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install countbot-ai/CountBot agent-team-manager --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/countbot-ai/CountBot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workspace/skills/agent-team-manager .claude/skills/agent-team-manager && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agent-team-manager" agent skill from https://github.com/countbot-ai/CountBot/tree/main/workspace/skills/agent-team-manager into .claude/skills/agent-team-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team-manager", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/countbot-ai/CountBot/tree/main/workspace/skills/agent-team-managerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add countbot-ai/CountBot --skill agent-team-manager -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install countbot-ai/CountBot agent-team-manager --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/countbot-ai/CountBot.git skills-src && mkdir -p .agents/skills && cp -r skills-src/workspace/skills/agent-team-manager .agents/skills/agent-team-manager && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-team-manager" agent skill from https://github.com/countbot-ai/CountBot/tree/main/workspace/skills/agent-team-manager into .agents/skills/agent-team-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team-manager", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add countbot-ai/CountBot --skill agent-team-manager -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install countbot-ai/CountBot agent-team-manager --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/countbot-ai/CountBot.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/workspace/skills/agent-team-manager .cursor/skills/agent-team-manager && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agent-team-manager" agent skill from https://github.com/countbot-ai/CountBot/tree/main/workspace/skills/agent-team-manager into .cursor/skills/agent-team-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team-manager", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/countbot-ai/CountBot.git --path workspace/skills/agent-team-manager--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add countbot-ai/CountBot --skill agent-team-manager -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install countbot-ai/CountBot agent-team-manager --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/countbot-ai/CountBot.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/workspace/skills/agent-team-manager .gemini/skills/agent-team-manager && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agent-team-manager" agent skill from https://github.com/countbot-ai/CountBot/tree/main/workspace/skills/agent-team-manager into .gemini/skills/agent-team-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team-manager", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install countbot-ai/CountBot agent-team-managerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add countbot-ai/CountBot --skill agent-team-manager -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/countbot-ai/CountBot.git skills-src && mkdir -p .github/skills && cp -r skills-src/workspace/skills/agent-team-manager .github/skills/agent-team-manager && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agent-team-manager" agent skill from https://github.com/countbot-ai/CountBot/tree/main/workspace/skills/agent-team-manager into .github/skills/agent-team-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team-manager", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add countbot-ai/CountBot --skill agent-team-manager -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install countbot-ai/CountBot agent-team-manager --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/countbot-ai/CountBot.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/workspace/skills/agent-team-manager .opencode/skills/agent-team-manager && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agent-team-manager" agent skill from https://github.com/countbot-ai/CountBot/tree/main/workspace/skills/agent-team-manager into .opencode/skills/agent-team-manager/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-team-manager", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agent-team-manager- GitHub stars
- 782
- Token cost
- ~1.6k tokens
- SKILL.md length
- 236 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属模型时使用。
- Works in 4 steps: 先读取当前真实配置，不允许凭印象修改 → 字段归属判定规则 → 执行规范 → …
- AI & LLM Engineering work in your project
- SKILL.md covers 使用场景, 调用方式, 严格语法 and 常用命令, plus 5 more sections
- Runs Python scripts from its folder; calls python3
What it does
Agent Team Manager is an agent skill from countbot-ai/CountBot. 多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属模型时使用。
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/agent_team_manager.py`).
It sits in AI & LLM Engineering. The repository describes itself as: 更适配中文用户的轻量开源AI Agent | 国产大模型Coding plan支持 | 兼容OpenClaw Skills生态| 已接入微信ClawBot/微博龙虾/飞书/钉钉/QQ/小智AI/Telegram/deepseek-v4。 The licence is MIT.
When your agent uses it
- AI & LLM Engineering work in your project
Example prompts
- “/agent-team-manager”
Requirements
- Python 3
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3c26f11. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agent Team Manager loads about 1.6k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 236 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from countbot-ai/CountBot at commit 3c26f11, republished under its MIT licence (© countbot-ai). 236 words, ~1,579 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-team-manager/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- agent-team-manager
- description
- 多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属模型时使用。
- version
- 1.0.0
- always
- false
多智能体团队管理
通过命令行管理 CountBot 的多智能体团队，覆盖团队 CRUD、成员 CRUD、以及团队级模型配置。
使用场景
- 用户说“帮我新建一个多智能体团队” -> 创建团队
- 用户说“做一个文档深度分析团队” -> 按模板创建团队
- 用户说“把这个团队改成依赖图模式” -> 修改团队
- 用户说“给团队加一个审稿角色” -> 添加成员
- 用户说“把 analyzer 的任务改一下” -> 修改成员
- 用户说“把这个角色的提示词优化一下” -> 先看当前成员配置，再修改
task和/或system_prompt - 用户说“删掉 summarizer 这个角色” -> 删除成员
- 用户说“给这个团队单独配置模型” -> 配置团队自定义模型
- 用户说“看看有哪些团队/成员” -> 列表或详情
调用方式
所有操作通过 exec 工具执行：
python3 skills/agent-team-manager/scripts/agent_team_manager.py <command> [args]严格语法
- 只有这些一级命令：
list、info、template-list、create、update、delete、member-list、member-add、member-update、member-delete、config、config-set、config-reset info/member-list/update/config-set的团队参数都是位置参数，不支持--teammember-update的成员参数是第二个位置参数member_ref，不支持--id- 开关技能系统要用团队命令
update "团队名" --enable-skills或--disable-skills - 先看
--help，再按帮助里的位置参数顺序执行；不要自行发明子命令或参数名
常用命令
列出团队
python3 skills/agent-team-manager/scripts/agent_team_manager.py list查看团队详情
team_ref 支持团队名称、完整 ID、ID 前缀。
python3 skills/agent-team-manager/scripts/agent_team_manager.py info "文档深度分析"创建团队
# 创建空团队，后续再逐个添加成员
python3 skills/agent-team-manager/scripts/agent_team_manager.py create \
--name "文档深度分析" \
--description "理解文档 → 提取要点 → 分析问题 → 生成总结报告" \
--mode pipeline \
--enable-skills
# 直接按内置模板创建
python3 skills/agent-team-manager/scripts/agent_team_manager.py create \
--template document-analysis修改团队
python3 skills/agent-team-manager/scripts/agent_team_manager.py update "文档深度分析" \
--mode graph \
--description "先并行抽取，再汇总结论" \
--active
python3 skills/agent-team-manager/scripts/agent_team_manager.py update "文档深度分析" \
--disable-skills删除团队
python3 skills/agent-team-manager/scripts/agent_team_manager.py delete "文档深度分析"成员管理
列出成员
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-list "文档深度分析"添加成员
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-add "文档深度分析" \
--id reader \
--role "文档理解专家" \
--task "通读文档，理解整体结构和核心内容" \
--system-prompt "你是文档理解专家，先识别文档结构，再提炼核心主题。"Graph 模式可附带依赖与条件：
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-add "代码检查团队" \
--id refactor \
--role "重构建议专家" \
--task "基于前序检查结果给出重构建议" \
--depends-on syntax-checker,logic-analyzer \
--condition-type output_contains \
--condition-node logic-analyzer \
--condition-text 严重Council 模式建议填写 --perspective：
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-add "投资评审会" \
--id risk \
--role "风险分析师" \
--perspective "风险与合规"修改成员
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-update "文档深度分析" analyzer \
--task "重点分析论证链、信息缺口和潜在偏见" \
--system-prompt "你是批判性分析专家，输出问题、证据和风险。"修改现有角色提示词（强约束）
凡是用户表达以下意图，统一按“修改现有角色提示词”处理：
- 优化角色提示词
- 改 prompt / 改系统提示词
- 调整角色设定、语气、边界、输出要求
- 让某个成员“更专业 / 更严格 / 更像某类专家”
强制执行顺序如下。
1. 先读取当前真实配置，不允许凭印象修改
python3 skills/agent-team-manager/scripts/agent_team_manager.py info "文档深度分析"必须先看目标成员当前是否存在 task、system_prompt，再决定修改哪个字段。
禁止在未读取当前配置前直接生成 member-update 命令。
2. 字段归属判定规则
- 若目标成员只有
task，没有system_prompt - 说明该团队把提示词主体直接存放在
task - 此时用户说“改提示词”，默认优先修改
--task - 若目标成员已有
system_prompt - 涉及角色人格、专家身份、口吻、原则、边界、长期行为约束时，优先修改
--system-prompt - 涉及具体工作内容、执行步骤、输出结构、交付格式、检查项时，优先修改
--task - 若当前
task本身是一整段提示词式文本，且用户想做系统化重构，应同时修改--task与--system-prompt
3. 执行规范
- 修改必须落库，最终动作一定是执行
member-update member-update的正确形式是：python3 skills/agent-team-manager/scripts/agent_team_manager.py member-update "团队名" 成员ID [flags]- 成员标识使用位置参数
member_ref，不要写成--id - 修改完成后，建议再次执行
info "团队名"复核结果 - 如果用户要求“修改提示词”，但当前配置里只有
task，不要只改system_prompt - 如果用户要求“系统提示词更专业”，但旧的长提示还残留在
task中，应判断是否需要同步精简task
示例：当前成员只有 task，没有 system_prompt
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-update "小红书文案团队" reviewer \
--task "审核小红书文案，检查敏感词、风格统一、内容完整、平台规范和可读性；输出审核结论、修改建议、最终发布版与发布提醒。"示例：明确修改系统提示词
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-update "小红书文案团队" reviewer \
--system-prompt "你是严格的小红书内容审核专家，优先识别违规风险和夸大表达，输出结论必须清晰、克制、可执行。"示例：把旧的提示词式 task 拆成“任务 + 系统提示词”
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-update "小红书文案团队" reviewer \
--task "审核小红书文案并输出审核结论、修改建议、最终发布版与发布提醒。" \
--system-prompt "你是严格的小红书内容审核专家，重点检查敏感词、极限词、医疗宣称、风格统一、内容完整和平台规范。"4. 专业处理原则
- 目标是“修改有效配置”，不是“输出一段看起来更好的文案”
- 先识别现有数据结构，再决定改哪个字段
- 以最小必要修改为原则，避免只新增字段而保留旧冲突内容
- 若用户未指定字段名，“提示词”一词要结合当前存储结构解释，不得机械等同于
system_prompt
删除成员
python3 skills/agent-team-manager/scripts/agent_team_manager.py member-delete "文档深度分析" summarizer团队模型配置
查看当前配置
python3 skills/agent-team-manager/scripts/agent_team_manager.py config "文档深度分析"设置自定义模型
python3 skills/agent-team-manager/scripts/agent_team_manager.py config-set "文档深度分析" \
--provider zhipu \
--model glm-5 \
--temperature 0.5 \
--max-tokens 8192重置为全局默认
python3 skills/agent-team-manager/scripts/agent_team_manager.py config-reset "文档深度分析"参数说明
mode仅支持pipeline、graph、council--enable-skills开启后，子 Agent 可读取并使用skills/*--cross-review/--no-cross-review仅对council模式有意义depends_on仅对graph模式有意义perspective主要用于council模式task会作为执行阶段的# Your Task传给子 Agent，是实际任务说明system_prompt是角色长期人格/职责设定- 如果
system_prompt为空，系统会基于role + task自动生成默认系统提示词 - 如果
system_prompt有值，会直接作为系统消息使用；但task仍然会继续传入执行提示中 - 因此：已有成员只有
task时，优先更新task；需要稳定角色口吻/边界时，再补或修改system_prompt - 很多历史团队把整段“提示词式描述”直接写进了
task，这不是脚本失效，而是数据本来就这样存的 - 所以“提示词改了没生效”时，优先检查是不是旧提示还躺在
task里
内置模板
当前内置：
document-analysis：文档深度分析，pipeline模式，默认开启技能系统
注意事项
- 团队名称必须唯一
- 成员 ID 在同一团队内必须唯一
- 修改成员本质上会读取团队详情后整体回写
agents - 如果团队启用了专属模型，执行
workflow_run(team_name="团队名", goal="...")时会自动继承该模型配置 - 如果 CountBot 后端未启动，脚本会直接报连接失败
© countbot-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (scripts) in workspace/skills/agent-team-manager of countbot-ai/CountBot.
- SKILL.md
- scripts/agent_team_manager.py
Open the folder on GitHubat commit 3c26f11
Compare with similar skills
Agent Team Manager next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agent Team Manager this skillcountbot-ai/CountBot | 782 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Agent BuildershareAI-lab/learn-claude-code | 78k | 6 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| Peft Fine TuningOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 9 repos | ~3.3k | Automated safety check: Pass | MIT | |
| 1passwordtrpc-group/trpc-agent-go | 1.8k | 15 repos | ~656 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
Peft Fine Tuning
Orchestra-Research/AI-Research-SKILLs
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
1password
trpc-group/trpc-agent-go
Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.
Chroma Vector Database
Orchestra-Research/AI-Research-SKILLs
Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.
More from countbot-ai/CountBot
All 11 skills in this repoIma Knowledge Base
countbot-ai/CountBot
通过 IMA OpenAPI 处理知识库任务。支持知识库内容搜索、命中详情查看、条目浏览、列出知识库、上传文件、导入网页。用户提到知识库、资料库、上传到知识库、导入网页、搜知识库时使用。
Find Skills
countbot-ai/CountBot
基于腾讯 SkillHub 搜索、安装和管理技能。用户提到“找技能”“安装 skill”“扩展功能”“启用/禁用 skill”“删除 skill”“安装 SkillHub CLI”时优先使用。
Image Analysis
countbot-ai/CountBot
图片分析与识别，可分析本地图片、网络图片、视频、文件。适用于 OCR、物体识别、场景理解等。当用户发送图片或要求分析图片时必须使用此技能。
Web Design
countbot-ai/CountBot
网页设计与部署。生成精美的单页 HTML 网页（报告、落地页、数据可视化等），支持一键部署到 Cloudflare Pages。使用 Tailwind CSS + Chart.js + Font Awesome 技术栈。当用户要求制作网页、生成报告页面、创建落地页、数据可视化展示、部署网页到线上时使用。
News
countbot-ai/CountBot
新闻与资讯查询。获取中文新闻和全球 AI 技术资讯，支持按分类查询（时政、财经、科技、社会、国际、体育、娱乐、AI 技术、AI 社区）。当用户询问最新新闻、AI 动态、行业资讯时使用。
Cron Manager
countbot-ai/CountBot
定时任务管理。创建、查看、修改、删除定时任务，管理任务会话数据。当用户需要设置提醒、定时执行任务、管理调度计划时使用. An agent skill from countbot-ai/CountBot.
Related
Categories
Questions about Agent Team Manager
What does Agent Team Manager do?
多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属模型时使用。. Agent Team Manager is an agent skill from countbot-ai/CountBot.
When should I use Agent Team Manager?
Agent Team Manager fits situations like: AI & LLM Engineering work in your project.
How do I install Agent Team Manager in Claude Code?
Run `npx skills add countbot-ai/CountBot --skill agent-team-manager -a claude-code`. Or copy the skill folder (workspace/skills/agent-team-manager in countbot-ai/CountBot) into .claude/skills/agent-team-manager in your project. Claude Code loads it when a task matches its description.
How do I install Agent Team Manager in Codex?
Run `npx skills add countbot-ai/CountBot --skill agent-team-manager -a codex`. Or copy the skill folder (workspace/skills/agent-team-manager in countbot-ai/CountBot) into .agents/skills/agent-team-manager in your project. Codex loads it when a task matches its description.
Can I use Agent Team Manager in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add countbot-ai/CountBot --skill agent-team-manager -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-team-manager, .gemini/skills/agent-team-manager, .github/skills/agent-team-manager and .opencode/skills/agent-team-manager in your project.
What does Agent Team Manager need to run?
Going by SKILL.md and its folder, Agent Team Manager needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Agent Team Manager access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Agent Team Manager safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Agent Team Manager use?
Agent Team Manager is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agent Team Manager use?
About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Agent Team Manager?
Skills that share tags, products or a category with Agent Team Manager: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), Peft Fine Tuning (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Team Manager?
countbot-ai (a GitHub user) maintains it in countbot-ai/CountBot, which has 782 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 4, 2026.
Source: countbot-ai/CountBot on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.