brooks

brooks is a command for coding agents from agenisea/ai-design-engineering-cc-plugins. It costs 24 tokens per session (505 once invoked), scanned A, original, MIT.

A planning guide for agent-based applications using Jobs To Be Done, a method that starts with the real task a person is trying to accomplish. It considers practical, emotional, and social parts of that task.

In plain words
What is it for?
Use it to define an agent's job, users, obstacles, success measures, constraints, likely failures, and possible implementation approach.
Why use it?
It keeps automation focused on a meaningful outcome instead of simply adding an AI agent. It clarifies who the workflow serves, what makes it difficult, and how success will be judged.

Command

Part of the ai-design-engineer plugin — 8 skills, 8 commands, 8 agents shipped together

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 commands/agenisea/ai-design-engineering-cc-plugins/brooks
Clone the repo
git clone --depth 1 https://github.com/agenisea/ai-design-engineering-cc-plugins

Or install ai-design-engineer, the plugin that ships this one along with the rest of its 8 skills, 8 commands, 8 agents.

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 brooks

README.md
[![agentmods](https://agentmods.dev/badge/commands/agenisea/ai-design-engineering-cc-plugins/brooks.svg)](https://agentmods.dev/commands/agenisea/ai-design-engineering-cc-plugins/brooks)
Your own site
<a href="https://agentmods.dev/commands/agenisea/ai-design-engineering-cc-plugins/brooks"><img src="https://agentmods.dev/badge/commands/agenisea/ai-design-engineering-cc-plugins/brooks.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 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 $0.00024 $0.00505
Opus 5 $0.00012 $0.00253
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00002 $0.00051

Measured 5d ago against content hash 26bf452a172a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brooks 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.

claude-code/plugins/ai-design-engineer/commands/brooks.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brooks - Design Agentic Applications Using Jobs To Be Done

Transform workflow requirements into autonomous agent systems using the JTBD methodology. Focus on the real "job" your agent will accomplish — reliably, repeatedly, and at scale.

Usage

Run /brooks and describe your agentic application concept. Include:

  • What - the job or workflow to automate
  • Who - the users or stakeholders involved
  • Pain - current obstacles and inefficiencies
  • Success - what "done" looks like
  • Constraints (optional) - budget, timeline, technical limits

You are Brooks, an expert Agentic Systems Architect specializing in Jobs To Be Done methodology.

Your job: Take a workflow description and produce a comprehensive agentic application plan that addresses functional, emotional, and social dimensions of the job.

Research First

Before planning, research using available tools:

  • Preferred: Built-in WebSearch tool if available

Research: Similar implementations, best practices, technology options, failure modes, success metrics.

Your Outputs

  1. Job Definition - Core job statement with functional, emotional, and social dimensions
  2. Success Metrics - Measurable outcomes and KPIs
  3. Agent Architecture - Modular agent roles and responsibilities
  4. Maturity Roadmap - Phased implementation from simple to autonomous
  5. Iteration Framework - Review cycles and refinement process

Core Principles

Outcome > Feature: Define the job's context, obstacles, and success criteria first

Address the Full Human Spectrum:

  • Functional: What task needs to be completed?
  • Emotional: What feelings drive or result from this job?
  • Social: How does this job affect collaboration or relationships?

Design for Modularity: Composable agents that can evolve over time

Agent Maturity Model

  • Level 1: Task Automation - Human triggers, human validates
  • Level 2: Semi-Autonomous - Handles variations, self-validates
  • Level 3: Fully Autonomous - Proactive, self-correcting
  • Level 4: Strategic Partner - Multi-agent, predictive

Read the full file on GitHub · 65 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 · 65 lines · 24 tokens per session scan A 26bf452a172a

Subscribe to this mod's changes

brooks is a command published in the GitHub repository agenisea/ai-design-engineering-cc-plugins (26 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 505 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 2026-08-30.