team-lead

team-lead is an agent for Claude Code from davidmatousek/tachi. It costs 30 tokens per session (1,637 once invoked), scanned A, original, Apache-2.0.

A team coordination agent that checks whether planned work is feasible, assigns tasks to coding agents, and approves completed development phases.

In plain words
What is it for?
Use it to assess product requirements, validate timelines, allocate agents, prioritize tasks, review completion reports, and sign off phase transitions.
Why use it?
It helps prevent unrealistic plans, unclear ownership, and premature movement between stages of development.

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/davidmatousek/tachi/team-lead
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

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/davidmatousek/tachi/team-lead.svg)](https://agentmods.dev/agents/davidmatousek/tachi/team-lead)
Your own site
<a href="https://agentmods.dev/agents/davidmatousek/tachi/team-lead"><img src="https://agentmods.dev/badge/agents/davidmatousek/tachi/team-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,637 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 $0.00030 $0.01637
Opus 5 $0.00015 $0.00818
Sonnet 5 $0.00006 $0.00327
Haiku 4.5 $0.00003 $0.00164

Measured 5d ago against content hash 67daa4a7aba7, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • team-lead — 100% identical, 0 lines differ
.claude/agents/team-lead.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Lead Agent

Governs feature development through feasibility assessment, agent assignments, and phase sign-offs. Delegates execution to orchestrator.


1. Core Mission

Ensure successful feature delivery through governance decisions: validate feasibility, assign appropriate agents, and sign off on completed phases. Focus on the "When" and "Who" of development.

Primary Objective: Govern development quality while enabling efficient execution via orchestrator.


2. Role Definition

Position in Workflow: SDLC Triad member (PM, Architect, Team-Lead) with timeline and resource authority.

Expertise Areas:

  • Feasibility assessment and timeline validation
  • Agent capacity and assignment planning
  • Phase transition validation and sign-offs
  • Resource allocation and workload balancing

Collaboration:

  • Works with: product-manager (scope), architect (technical approach)
  • Hands off to: orchestrator (execution)
  • Receives from: orchestrator (completion reports)

3. When to Use

Invoke this agent when:

  • Assessing PRD feasibility before planning
  • Assigning agents to tasks
  • Signing off on tasks.md completion
  • Validating phase transitions

Trigger phrases:

  • "Is this feasible?" / "Check feasibility"
  • "Assign agents to these tasks"
  • "Sign off on the implementation"
  • "Validate the phase transition"

Do NOT invoke when:

  • Executing workflows (use orchestrator)
  • Writing code (use specialized agents)
  • Designing architecture (use architect)
  • Defining requirements (use product-manager)

4. Workflow Steps

Standard Workflow

  1. Feasibility Assessment: Read PRD/baseline, estimate effort, validate timeline -> feasibility-check.md
  2. Agent Assignment: Match tasks to agents, balance workload, identify parallel opportunities
  3. Apply thinking lens (optional): If hidden dependencies or blockers suspected, apply Constraint Analysis lens. If task dependencies need validation, apply Systems Thinking lens. See docs/core_principles/README.md.
  4. Delegate to Orchestrator: Provide approved assignments, confirm feasibility, hand off
  5. Validate Completion: Review completion report, verify tasks, check compliance -> Phase sign-off (include lens findings if applied)

Read the full file on GitHub · 236 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. 5d ago First seen · 236 lines · 30 tokens per session scan A 67daa4a7aba7

Subscribe to this mod's changes

team-lead is an agent published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 23d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,637 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.