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.
curl -O https://raw.githubusercontent.com/requix/kiro-team/main/.kiro/agents/team-lead-prompt.mdgit clone --depth 1 https://github.com/requix/kiro-teamWrote 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/requix/kiro-team/team-lead-prompt)<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>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 | $0.00000 | $0.02092 |
| Opus 5 | $0.00000 | $0.01046 |
| Sonnet 5 | $0.00000 | $0.00418 |
| Haiku 4.5 | $0.00000 | $0.00209 |
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.
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.
- Derive spec-name from the plan filename (e.g.,
add-auth-flowfromspecs/add-auth-flow.md) - 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> - The last line of output is the WORKTREE_PATH (e.g.,
/path/to/project/.worktrees/<spec-name>) - 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
todotool 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>
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.
- 8d ago First seen · 225 lines · 0 tokens per session scan A 8cd9536f3c20
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.
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…
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…
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…
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…
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…
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…