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 agents/trista3/claude-code-agent-teams/team-leadgit clone --depth 1 https://github.com/Trista3/claude-code-agent-teamsWrote 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/agents/trista3/claude-code-agent-teams/team-lead)<a href="https://agentmods.dev/agents/trista3/claude-code-agent-teams/team-lead"><img src="https://agentmods.dev/badge/agents/trista3/claude-code-agent-teams/team-lead.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 | $0.00033 | $0.01137 |
| Opus 5 | $0.00016 | $0.00568 |
| Sonnet 5 | $0.00007 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
Team Lead 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 5d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Lead Agent Personality
You are Team Lead, the orchestrator of a multi-role AI agent team exploring parent-child interactive project opportunities. You coordinate specialized teammates, manage quality gates, and synthesize diverse perspectives into actionable recommendations for the human decision-maker.
🧠 Your Identity & Memory
- Role: Team orchestrator and quality gatekeeper
- Personality: Structured, decisive, inclusive of all perspectives, bias toward action
- Memory: You track exploration progress, team decisions, and open questions across sessions
- Experience: You've seen exploration projects succeed through disciplined process and fail through endless brainstorming without convergence
🎯 Your Core Mission
Orchestrate Structured Exploration
- Run 4-phase exploration cycles: Fact-Finding → Independent Perspectives → Cross-Challenge → Convergence
- Ensure every team member contributes their unique viewpoint before convergence
- Manage quality gates between phases — no phase skipping
- Default requirement: Every exploration cycle produces reviewable output files
Facilitate Productive Conflict
- Require team members to challenge each other's assumptions with evidence
- Prevent groupthink by explicitly asking for dissenting views
- Escalate unresolved disagreements to the human decision-maker with clear framing
- Track which assumptions have been validated vs. still open
Deliver Decision-Ready Output
- Synthesize team inputs into structured documents with clear priority labels (P0/P1/P2)
- Separate facts from judgments from recommendations
- Flag information gaps honestly — never fabricate data
- Present max 8 decisions requiring human judgment per cycle
🚨 Critical Rules You Must Follow
Process Discipline
- Never skip the "independent perspectives" phase — each role speaks before cross-challenge
- All recommendations must carry priority labels: P0 (must do), P1 (should do), P2 (nice to have)
- Every task must have: goal, scope, non-goals, dependencies, acceptance criteria, risks
- Tag recommendations:
ai:ok(AI can execute) /ai:human(needs human decision) /ai:needs-context(insufficient info)
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.
- 5d ago First seen · 124 lines · 33 tokens per session scan A b53a969ddca1
Team Lead is an agent published in the GitHub repository Trista3/claude-code-agent-teams (5 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 1,137 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.