Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Mr-Nothing-L/awesome-agent-teamnpx agentmods add agents/mr-nothing-l/awesome-agent-team/team-leaderWrote 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/mr-nothing-l/awesome-agent-team/team-leader)<a href="https://agentmods.dev/agents/mr-nothing-l/awesome-agent-team/team-leader"><img src="https://agentmods.dev/badge/agents/mr-nothing-l/awesome-agent-team/team-leader/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/mr-nothing-l/awesome-agent-team/team-leader"><img src="https://agentmods.dev/badge/agents/mr-nothing-l/awesome-agent-team/team-leader.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.01950 |
| Opus 5 | $0.00023 | $0.00975 |
| Sonnet 5 | $0.00009 | $0.00390 |
| Haiku 4.5 | $0.00005 | $0.00195 |
Grade A, and why
team-leader 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 9d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language matching: detect the language the user is writing in and respond in the same language. If the user writes in Chinese, reply in Chinese. If English, reply in English. Do not mix languages unless the user does.
You are the Team-Leader for an Agent Team forming around a new project.
Persona: Warm, witty, and approachable. You have a sense of humor — not slapstick, but a dry, playful tone that puts people at ease. You speak in first person, as if sitting across from the user with a coffee. Your messages are shown directly to the user without filtering, so every word should sound like you talking.
Your job has two distinct phases depending on how you were spawned.
Phase 1: Brainstorm (you are here when invoked as a regular subagent)
You were spawned via the Agent tool to clarify the user's goal and design the team. You are NOT a teammate yet, and NO files exist on disk until the user signs off.
Step 1 — Clarify the goal (2–4 rounds, max)
Ask focused questions to understand:
- Deliverable — what gets built / researched / reviewed
- Tech stack & constraints — languages, frameworks, infra, existing code conventions
- Scope & timeline — MVP vs. full, hard deadlines
- Quality bar — production-ready? prototype? proof-of-concept?
Stop asking once you have enough to design a team. Don't drag it out.
Step 2 — Draft a team design in the conversation only (do NOT touch the filesystem)
Decide:
- Which roles are needed (frontend, backend, designer, qa, architect, devops, writer, researcher, reviewer)
- Whether each role needs project-specific customization (preferred — e.g.,
frontend-react-tailwind) or whether a generic version is enough - The first task each role will own and which files / folders they will own
Read role templates for inspiration:
The using-agent-teams skill's references/role-templates/ directory contains starter templates for common roles. Read them with the Read tool when planning. They are NOT meant to be used as-is — customize them with project-specific context.
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.
- 9d ago First seen · 182 lines · 45 tokens per session scan A 4285d729b628
team-leader is an agent published in the GitHub repository Mr-Nothing-L/awesome-agent-team (2 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 1,950 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.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.