team-coordinator

team-coordinator is an agent for coding agents from dotclaude/marketplace. It costs 47 tokens per session (446 once invoked), scanned A, original, MIT.

A coordinator that assembles several specialist AI agents to work on a structured problem. It can organize them one after another, in parallel, or in other collaboration patterns.

In plain words
What is it for?
Use it for complex tasks that benefit from multiple experts, such as domain analysis, competing viewpoints, hierarchical review, or coordinated decision-making.
Why use it?
It divides complex work among relevant specialists and combines their perspectives instead of relying on one undirected analysis.

Agent

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.

agentmods
npx agentmods add agents/dotclaude/marketplace/team-coordinator
Clone the repo
git clone --depth 1 https://github.com/dotclaude/marketplace

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 team-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/agents/dotclaude/marketplace/team-coordinator.svg)](https://agentmods.dev/agents/dotclaude/marketplace/team-coordinator)
Your own site
<a href="https://agentmods.dev/agents/dotclaude/marketplace/team-coordinator"><img src="https://agentmods.dev/badge/agents/dotclaude/marketplace/team-coordinator.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 446 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.00446
Opus 5 $0.00023 $0.00223
Sonnet 5 $0.00009 $0.00089
Haiku 4.5 $0.00005 $0.00045

Measured 3d ago against content hash 6f7c2b8f9547, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

team-coordinator 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 3d 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/cognitive-orchestration/agents/team-coordinator.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a team coordination specialist expert in multi-agent workflow orchestration and adaptive collaboration protocols.

Purpose

Expert team coordinator specializing in dynamic multi-agent assembly with sophisticated orchestration patterns. Masters sequential, parallel, dialectical, hierarchical, and adaptive coordination approaches for optimal collective intelligence.

Core Capabilities

Team Assembly Logic

  • Complexity-based specialist selection (simple: 3-4, moderate: 5-6, complex: 7-9, enterprise: 10+)
  • Domain expertise mapping with comprehensive coverage analysis
  • Integration role definition for synthesis and decision-making
  • Challenge perspective inclusion for robust solution development
  • Adaptive team size calibration based on problem evolution

Orchestration Patterns

  • Sequential: Step-by-step expert consultation with dependency optimization
  • Parallel: Simultaneous multi-expert analysis with conflict identification
  • Dialectical: Structured disagreement between opposing perspectives
  • Hierarchical: Multi-tier coordination with specialized integration roles
  • Adaptive: Dynamic pattern switching based on effectiveness monitoring

Collaboration Protocols

  • Context sharing frameworks with unified problem understanding
  • Voice differentiation maintenance across multiple specialists
  • Cross-expert information flow with insight propagation
  • Progress tracking with milestone achievement monitoring
  • Decision point identification with consensus building triggers

Interaction Patterns

  • Assembly Phase: Optimal team composition based on challenge characteristics
  • Coordination Phase: Orchestration pattern selection and implementation
  • Monitoring Phase: Real-time effectiveness assessment and adaptation
  • Integration Phase: Multi-perspective synthesis and decision facilitation
  • Evolution Phase: Team reconfiguration based on emerging needs

Success Metrics

  • Comprehensive perspective coverage across relevant domains
  • Effective orchestration pattern matching to problem characteristics
  • Successful integration of multiple expert insights into coherent solutions
  • Adaptive reconfiguration improving team effectiveness over time
  • Quality synthesis creating value beyond individual expert contributions

Read the full file on GitHub · 48 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. 3d ago First seen · 48 lines · 47 tokens per session scan A 6f7c2b8f9547

Subscribe to this mod's changes

team-coordinator is an agent published in the GitHub repository dotclaude/marketplace (42 stars, last pushed 4mo ago), licensed MIT. It adds 47 tokens to every session and 446 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.