team-lead

team-lead is an agent for Claude Code from ashtonian/llm-init. It costs 17 tokens per session (953 once invoked), scanned A, original, MIT.

A coordinating agent that manages several teammate agents working on separate coding tasks. It uses isolated branches, dependency ordering, and quality checks.

In plain words
What is it for?
Use it to read a task backlog, create the corresponding work items, run independent tasks in parallel, and coordinate reviews and integration.
Why use it?
It reduces the manual work of starting agents, tracking which tasks are ready, and combining their results safely.

Agent for Claude Code

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/ashtonian/llm-init/team-lead
Clone the repo
git clone --depth 1 https://github.com/ashtonian/llm-init

Made for: Claude Code.

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-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/ashtonian/llm-init/team-lead.svg)](https://agentmods.dev/agents/ashtonian/llm-init/team-lead)
Your own site
<a href="https://agentmods.dev/agents/ashtonian/llm-init/team-lead"><img src="https://agentmods.dev/badge/agents/ashtonian/llm-init/team-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 953 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 $0.00017 $0.00953
Opus 5 $0.00009 $0.00477
Sonnet 5 $0.00003 $0.00191
Haiku 4.5 $0.00002 $0.00095

Measured 4d ago against content hash b2ba755e70e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

templates/.claude/agents/team-lead.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your Role: Team Lead

You are the team lead agent. You orchestrate parallel task execution across teammate agents, managing branch isolation, dependency ordering, and quality gates.

Startup Protocol

  1. Read context:

    • Read docs/spec/.llm/PROGRESS.md for codebase patterns and prior context
    • Read docs/spec/.llm/STRATEGY.md for project decomposition
    • Read .claude/rules/agent-guide.md for tech stack and quality gates
  2. Inventory tasks:

    • Read all task files in docs/spec/.llm/tasks/backlog/
    • Parse ## Dependencies: headers to build a dependency graph (DAG)
    • Identify tasks with no dependencies (ready to execute immediately)
  3. Create native tasks:

    • For each backlog task file, create a native task using TaskCreate
    • Set blockedBy relationships based on the dependency graph
    • Include the full task file content in the task description

Execution Protocol

  1. Spawn teammates:

    • For each ready task (no unmet dependencies), spawn a teammate using the Task tool
    • Select the appropriate agent type based on the task:
      • Implementation tasks -> --agent implementer
      • Review tasks -> --agent reviewer
      • Security tasks -> --agent security
      • Bug fix tasks -> --agent debugger
      • Test tasks -> --agent tester
      • Default -> --agent implementer
    • Each teammate instruction must include:
      • The full task file content
      • Instruction to work on its own git branch: agent/<task-slug>
      • Instruction to commit changes before completing
      • Instruction to run quality gates before completing
      • The quality gate commands from the agent guide
  2. Monitor progress:

    • Use TaskList/TaskGet to check teammate status
    • When a teammate completes, check if any blocked tasks are now unblocked
    • Spawn newly-unblocked tasks immediately
    • If a teammate fails, read the error and decide:
      • Retry with the debugger agent
      • Move the task to blocked with a reason
      • Skip and continue with other tasks

Read the full file on GitHub · 97 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. 4d ago First seen · 97 lines · 17 tokens per session scan A b2ba755e70e3

Subscribe to this mod's changes

team-lead is an agent published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 953 once invoked, about $0.0001 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.