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/davidmatousek/tachi/team-leadgit clone --depth 1 https://github.com/davidmatousek/tachiWrote 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/davidmatousek/tachi/team-lead)<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>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 | $0.00030 | $0.01637 |
| Opus 5 | $0.00015 | $0.00818 |
| Sonnet 5 | $0.00006 | $0.00327 |
| Haiku 4.5 | $0.00003 | $0.00164 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- team-lead — 100% identical, 0 lines differ
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
- Feasibility Assessment: Read PRD/baseline, estimate effort, validate timeline ->
feasibility-check.md - Agent Assignment: Match tasks to agents, balance workload, identify parallel opportunities
- 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. - Delegate to Orchestrator: Provide approved assignments, confirm feasibility, hand off
- Validate Completion: Review completion report, verify tasks, check compliance -> Phase sign-off (include lens findings if applied)
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 · 236 lines · 30 tokens per session scan A 67daa4a7aba7
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.
Other agents, from other repositories
jethro
COO agent for business operations, MSP/MSSP service delivery, client onboarding, SLA management, capacity planning, vendor management, operational metrics, and M&A integration. Use when user mentions operations, service delivery, onboarding, SLA, capacity planning, vendor management, client health, operational…
CLAUDE
This guide provides instructions for creating cs- prefixed agents that orchestrate the USAP skill packages.
joshua
DevTeam Project Manager that breaks architecture into tasks, manages dependencies, dispatches developer agents, monitors progress, and coordinates QA/review cycles. USE WHEN orchestrating multi-agent development teams, managing TODO.md task boards, or coordinating parallel coding agents.
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.