Is the Agent Team Manager skill free?

Yes. The skill itself is free from countbot-ai/CountBot. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Team Manager SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Agent Team Manager?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Team Manager with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Team Manager

CLI to manage CountBot multi-agent teams: CRUD, members, per-team models

by countbot-ai · countbot-ai/CountBot

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.8/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · bf50fc4

Booted a real CountBot backend (uvicorn plus SQLite) and ran the skill end to end: template create, member add, task rewrite, team model config (zhipu/glm-5), and a pipeline-to-graph mode switch all succeeded first try with zero syntax errors, exactly as the strict-syntax notes promise. The docs are unusually honest — the documented positional-argument pitfalls and the 'prompt lives in task, not system_prompt' guidance both matched real behavior. The baseline is harder than it looks: the backend exposes no /openapi.json, and member updates require a whole-array read-modify-write that the script handles for you. The catch: nothing works until you install and launch the full CountBot application on localhost:8000 — this is a companion skill to that product, not a standalone tool.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Agent Team Manager does

Command-line management of multi-agent teams for the CountBot framework: create teams from templates, run pipeline/graph/council modes, add or rewrite member roles and prompts, and set team-specific model configs via the local REST API. Triggers when a user asks to create or modify a CountBot agent team, adjust member roles or dependencies, or configure a team's model. Requires a running CountBot backend on localhost:8000.

How to install Agent Team Manager

git clone --depth 1 https://github.com/countbot-ai/CountBot
mkdir -p ~/.claude/skills
cp -r CountBot/workspace/skills/agent-team-manager ~/.claude/skills/agent-team-manager

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agent Team Manager

/agent-team-manager CLI to manage CountBot multi-agent teams: CRUD, members, per-team models

It also activates on plain-language prompts like these:

Create a document-analysis agent team from the built-in template
Add a reviewer member to my agent team with a custom prompt
Switch my agent team from pipeline mode over to graph mode

Frequently asked questions

Is the Agent Team Manager skill free?: Yes. The skill itself is free from countbot-ai/CountBot. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Team Manager work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. Booted a real CountBot backend (uvicorn plus SQLite) and ran the skill end to end: template create, member add, task rewrite, team model config (zhipu/glm-5), and a pipeline-to-graph mode switch all succeeded first try with zero syntax errors, exactly as the strict-syntax notes promise. The docs are unusually honest — the documented positional-argument pitfalls and the 'prompt lives in task, not system_prompt' guidance both matched real behavior. The baseline is harder than it looks: the backend exposes no /openapi.json, and member updates require a whole-array read-modify-write that the script handles for you. The catch: nothing works until you install and launch the full CountBot application on localhost:8000 — this is a companion skill to that product, not a standalone tool.
What is the Agent Team Manager SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Agent Team Manager?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Team Manager with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.