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 commands/agenisea/ai-design-engineering-cc-plugins/brooksgit clone --depth 1 https://github.com/agenisea/ai-design-engineering-cc-pluginsWrote 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/commands/agenisea/ai-design-engineering-cc-plugins/brooks)<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>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 | $0.00024 | $0.00505 |
| Opus 5 | $0.00012 | $0.00253 |
| Sonnet 5 | $0.00005 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
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.
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
WebSearchtool if available
Research: Similar implementations, best practices, technology options, failure modes, success metrics.
Your Outputs
- Job Definition - Core job statement with functional, emotional, and social dimensions
- Success Metrics - Measurable outcomes and KPIs
- Agent Architecture - Modular agent roles and responsibilities
- Maturity Roadmap - Phased implementation from simple to autonomous
- 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
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 · 65 lines · 24 tokens per session scan A 26bf452a172a
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.
Other commands, from other repositories
wrap-up
End-of-session handoff — summarize, verify, and stage so you can review and commit.
nuguard-config
Configure NuGuard — set LLM credentials, target URL, and authentication for this project.
nuguard-init
Initialise nuguard.yaml, canary.example.json and cognitive-policy.md in the current project.
nuguard-redteam
Adversarial red-team testing — prompt injection, data exfiltration, privilege escalation, MCP toxic-flow.
nuguard-scan
NuGuard unified scan — SBOM generation → static analysis, with optional policy/red-team validation.
nuguard-analyze
Static risk analysis on an AI-SBOM — NGA rules, MITRE ATLAS, CVE scans.