mastermind

A command that interprets what you want to do and sends you to the matching AB Method workflow. The AB Method is a project-development process with separate workflows for analysis, planning, implementation, and review.

In plain words
What is it for?
Use it as the starting point when you are unsure which workflow to run, such as creating a task, creating a goal, resuming work, or learning how the method is organized.
Why use it?
It removes the need to remember which command fits your situation. It can also explain how the available workflows connect and help choose between a task and a longer autonomous goal.

Command for Claude Code

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/ayoubben18/ab-method/mastermind
Clone the repo
git clone --depth 1 https://github.com/ayoubben18/ab-method

Made for: Claude Code.

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 359 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 $0.00000 $0.00359
Opus 5 $0.00000 $0.00179
Sonnet 5 $0.00000 $0.00072
Haiku 4.5 $0.00000 $0.00036

Measured 2d ago against content hash 14743867032c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mastermind 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 2d 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/commands/mastermind.md · 41 lines

What it actually says

Mastermind

Description

The intelligent entry point to the AB Method. Figures out what you want to do and routes you to the right workflow — or explains how the method fits together end to end. Where /ab-master is a static menu, /mastermind reasons about your intent and hands off.

Usage

/mastermind [what you want to do]

Behavior

Loads and executes the mastermind workflow from .ab-method/core/mastermind.md.

It will:

  1. Always check .ab-method/structure/index.yaml first for the file layout.
  2. Discover available workflows at runtime from .ab-method/core/ — it does not carry a hardcoded catalogue.
  3. Match your intent and delegate to the matching workflow (e.g. /create-task, /create-goal, /resume-task) without reimplementing it.
  4. Help you decide goal vs task when that's the fork.
  5. Explain the AB Method end to end, grounded in the actual files, when asked.

Examples

/mastermind
# Asks what you're trying to accomplish, then routes you

/mastermind I want to add rate limiting to the API
# Recommends create-task (stay in the loop) and hands off

/mastermind explain how the ab method works
# Concise end-to-end tour: baseline → sharpen → build → maintain

Notes

  • Multi-task orchestration (idea → dependency-ordered roadmap → execution) lives in the /create-roadmap/start-roadmap pair. Mastermind routes to them; it doesn't hold that logic itself.
  • For the plain workflow menu, use /ab-master.
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. 2d ago First seen · 41 lines · 0 tokens per session scan A 14743867032c

Subscribe to this mod's changes

mastermind is a command published in the GitHub repository ayoubben18/ab-method (187 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 359 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.