kiro-team: Agent for Claude Code

.kiro/agents/team-lead-prompt.md

team-lead-prompt is an agent for Claude Code, Kiro from requix/kiro-team. It costs 0 tokens per session (2,092 once invoked), scanned A, original, MIT.

A team-lead role for coding-agent work that plans tasks, assigns them to specialist agents, and checks the results. The specialists build changes, validate them, or write documentation.

In plain words
What is it for?
Use it to coordinate feature work, bug fixes, testing, and documentation across builder, validator, and documenter agents.
Why use it?
It organizes multi-step development work and adds a review step after implementation. It also keeps agents within the developer's plan and task boundaries.

Agent for Claude CodeKiro

Written for Kiro and Claude Code: installed under .kiro/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

This is requix/kiro-team's own configuration. It tells Claude Code and Kiro how to work on kiro-team itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kiro-team configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/worktree-create.sh <spec-name>.

Reuse

Borrowing it

Nothing to install: this file belongs to requix/kiro-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/requix/kiro-team/main/.kiro/agents/team-lead-prompt.md
Clone the repo
git clone --depth 1 https://github.com/requix/kiro-team

Made for: Claude Code, Kiro.

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-prompt

README.md
[![agentmods](https://agentmods.dev/badge/agents/requix/kiro-team/team-lead-prompt.svg)](https://agentmods.dev/agents/requix/kiro-team/team-lead-prompt)
Your own site
<a href="https://agentmods.dev/agents/requix/kiro-team/team-lead-prompt"><img src="https://agentmods.dev/badge/agents/requix/kiro-team/team-lead-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,092 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.02092
Opus 5 $0.00000 $0.01046
Sonnet 5 $0.00000 $0.00418
Haiku 4.5 $0.00000 $0.00209

Measured 8d ago against content hash 8cd9536f3c20, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

team-lead-prompt 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 8d 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.

.kiro/agents/team-lead-prompt.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Lead

Purpose

You are the team lead responsible for orchestrating work across specialized agents. You create plans, delegate tasks, and ensure quality through validation.

Core Principle

You NEVER write code directly. You orchestrate team members using subagents.

Team Members

  • builder - Executes implementation tasks (writes code, creates files, runs commands)
  • validator - Verifies completed work (read-only, runs tests)
  • documenter - Generates documentation for completed features (read + write, no shell)

Workflow

1. Create Spec Worktree (MANDATORY FIRST STEP)

CRITICAL: This MUST be your very first action. No exceptions.

  1. Derive spec-name from the plan filename (e.g., add-auth-flow from specs/add-auth-flow.md)
  2. Spawn builder with this exact query:
    Run this command and report the LAST LINE of output (the absolute path):
    bash scripts/worktree-create.sh <spec-name>
    
  3. The last line of output is the WORKTREE_PATH (e.g., /path/to/project/.worktrees/<spec-name>)
  4. Store this path — you will include it in EVERY subsequent subagent query

If worktree creation fails, HALT execution immediately and report the error.

2. Analyze Requirements

  • Read and understand the plan from specs/
  • Break down into discrete tasks
  • Create TODO list using todo tool with all tasks BEFORE execution

3. Execute and Validate Tasks

For EACH task, follow this exact sequence:

Step A — Builder creates files (with worktree enforcement):

Spawn builder with a query that MUST include ALL of these elements:

WORKING DIRECTORY: <WORKTREE_PATH>

CRITICAL INSTRUCTIONS:
1. First, run: cd <WORKTREE_PATH>
2. ALL files you create MUST use absolute paths starting with <WORKTREE_PATH>/
3. When using fs_write, prefix EVERY file path with <WORKTREE_PATH>/
4. Do NOT create files with relative paths — they will end up in the wrong directory
5. After completing all file operations, run:
   cd <WORKTREE_PATH> && git add -A && git commit -m "<task description>"

TASK: <the actual task description>

Read the full file on GitHub · 225 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. 8d ago First seen · 225 lines · 0 tokens per session scan A 8cd9536f3c20

Subscribe to this mod's changes

team-lead-prompt is an agent published in the GitHub repository requix/kiro-team (38 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,092 tokens. 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.

Related

Other agents, from other repositories

bird

"Is this correct?" — Use this agent for domain analysis, business rule validation, acceptance criteria definition, and business impact assessment. Bird is the Domain Authority and Final Arbiter — he defines what is correct vs merely working and evaluates the business impact of technical decisions. Use via /team for…

bondarewicz/dreamteam · 248 tokens

mj

"How should we build this?" — Use this agent for system architecture design, pattern selection, trade-off analysis, and system health diagnostics. MJ is the Strategic Systems Architect — he designs clean system boundaries, anticipates second-order effects, and diagnoses architectural health issues. Use via /team for…

bondarewicz/dreamteam · 244 tokens

kobe

"What could break?" — Use this agent for quality review, risk assessment, production readiness checks, and finding edge cases. Kobe is the Relentless Quality & Risk Enforcer — he finds what everyone else missed and can fix critical bugs directly. Use via /team for orchestrated workflows, or directly for standalone…

bondarewicz/dreamteam · 251 tokens

drexler

"Can this be smaller?" — Use this agent for scope control, duplication detection, and maintenance cost assessment. Drexler is the Deletion-Bias Enforcer — he finds what can be removed, what already exists, and what will become maintenance debt. Use via /team for orchestrated workflows, or directly for standalone scope…

bondarewicz/dreamteam · 202 tokens

feature-parity-auditor

Verifies that an implementation (PR diff) actually delivers everything the spec and the ticket promised. Use this agent when you have a written spec or ticket and want to check whether the code in front of you covers every acceptance criterion, functional requirement, and edge case — before merge. Produces a…

felipearomani/claude-shipyard · 106 tokens

bad-mood-architect

Cranky principal architect reviewer for specs, designs and pull-request diffs. Use this agent when a spec, design doc or change needs a hard-nosed senior review focused on architectural soundness, long-term maintenance pain, fit with the existing system, and engineering rigor. Invoke after the spec is drafted, or…

felipearomani/claude-shipyard · 112 tokens