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 skills/bendrucker/claude/agent-teamnpx skills add bendrucker/claude --skill agent-teamgit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/agent-team)<a href="https://agentmods.dev/skills/bendrucker/claude/agent-team"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/agent-team.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00790 |
| Opus 5 | $0.00019 | $0.00395 |
| Sonnet 5 | $0.00008 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
claude-code:agent-team 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 yesterday.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Teams
Arguments
These select a team mode up front instead of toggling it interactively (see Team Lifecycle):
--delegate: start the lead in delegate mode, coordination-only with no direct implementation. Default: the lead can implement.--plan-approval: require teammates to plan before implementing, read-only until the lead approves. Default: off.--shutdown: shut the current team down, teammates first and then the team, then stop. Default: create or operate a team.
Team Lifecycle
Describe the task and team structure in natural language. Claude creates the team, spawns teammates, and coordinates work. Delegate mode also toggles interactively with Shift+Tab. Always shut down via the lead: teammates individually, then the team.
Task Management
Tasks: pending, in progress, completed. Tasks can depend on other tasks — blocked tasks unlock automatically when dependencies complete.
- Lead assigns: tell the lead which task to assign
- Self-claim: teammates pick up unassigned, unblocked tasks after finishing
- File locking prevents race conditions on simultaneous claims
Communication
- message: send to one specific teammate
- broadcast: send to all teammates (use sparingly — costs scale with team size)
- Messages deliver automatically; the lead doesn't need to poll
- Idle notifications are automatic when a teammate finishes a turn
Architecture
Teams are stored locally:
- Team config:
~/.claude/teams/{team-name}/config.json - Task list:
~/.claude/tasks/{team-name}/
The config contains a members array with each teammate's name, agent ID, and type. Teammates read this file to discover each other.
Teammates inherit the lead's permission settings at spawn. Each loads project context (CLAUDE.md, MCP servers, skills) plus the spawn prompt — the lead's conversation history does not carry over.
Limitations
- No session resumption for in-process teammates (
/resumewon't restore them) - Task status can lag — check and nudge if stuck
- One team per session, no nested teams
- Lead is fixed for the team's lifetime
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +1 lines b4787a1ebd43
- 4d ago First seen · 72 lines · 38 tokens per session scan A ea317f059c0d
claude-code:agent-team is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 790 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
codex-test-gen
Generate unit tests for specified functions using Codex MCP.
brand-docx
Brand-aware Word engine. Use to (1) EXTRACT a company's brand from a Word template into a reusable "Brand Profile", (2) COMPREHEND the template with the model (optional), (3) VERIFY it, (4) GENERATE new on-brand .docx documents FROM a saved profile. Trigger on "extract our brand", "learn/match this template", "use our…
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.