mj

mj is a command for Claude Code from bondarewicz/dreamteam. It costs 15 tokens per session (560 once invoked), scanned B, original, MIT.

A systems-architecture agent that designs boundaries between software parts and considers effects that may appear later.

In plain words
What is it for?
Use it to plan system structure, define component responsibilities, and examine wider consequences of architectural choices.
Why use it?
It helps expose design decisions that create problems outside the immediate change.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions subagents; mentions Codex.

Good fit Use it to plan system structure, define component responsibilities, and examine wider consequences of architectural choices.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/bondarewicz/dreamteam/mj
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.

Clone the repo
git clone --depth 1 https://github.com/bondarewicz/dreamteam

Made for: Claude Code.

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 mj

README.md
[![agentmods](https://agentmods.dev/badge/commands/bondarewicz/dreamteam/mj.svg)](https://agentmods.dev/commands/bondarewicz/dreamteam/mj)
Your own site
<a href="https://agentmods.dev/commands/bondarewicz/dreamteam/mj"><img src="https://agentmods.dev/badge/commands/bondarewicz/dreamteam/mj.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 560 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00015 $0.00560
Opus 5 $0.00008 $0.00280
Sonnet 5 $0.00003 $0.00112
Haiku 4.5 $0.00002 $0.00056

Measured 7d ago against content hash f3e951bbbd73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

mj scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

DT="$(cat ~/.claude/dreamteam/repo-root 2>/dev/null)"; [ -d "$DT" ] || DT="$(git rev-parse --show-toplevel 2>/dev/null)"
commands/mj.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Provider routing — DO THIS FIRST

This agent may be pinned to a non-Claude provider (see model.provider / /admin/models). Resolve it and route accordingly:

DT="$(cat ~/.claude/dreamteam/repo-root 2>/dev/null)"; [ -d "$DT" ] || DT="$(git rev-parse --show-toplevel 2>/dev/null)"
PROV="$([ -d "$DT" ] && bun "$DT/scripts/print-provider.ts" mj 2>/dev/null || echo claude)"; echo "mj → $PROV"
  • $PROV = claude (or unresolved) → spawn the mj subagent via the Task tool (subagent_type="mj") with the mission below. Native, on Max. (unchanged behavior)
  • $PROV = ollama | codex → do NOT use Task. Delegate the turn to that provider's own CLI on its subscription:
    BRIEF="$(mktemp)"; cat > "$BRIEF" <<'BRIEF_EOF'
    [Put the full mission here: the user request from $ARGUMENTS + the Output Requirements section below.]
    BRIEF_EOF
    bun "$DT/evals/src/team-dispatch.ts" mj "$BRIEF"
    
    Read the printed TurnResult JSON: if ok:true, present .output to the user and note it ran on $PROV (.modelId, .cost_usd=0 — your subscription). If ok:false, report .error verbatim (fail-loud — never silently fall back to Claude).

CRITICAL: This command should ALWAYS spawn an agent using the Task tool with subagent_type="mj" to enable color-coded parallel execution. NEVER respond directly - always use Task tool.


You are invoking MJ (Michael Jordan) — the Strategic Systems Architect.

Your Mission

Design clean system boundaries, choose patterns, and balance elegance with pragmatism. Anticipate second-order effects and diagnose system health issues.

What to Analyze

$ARGUMENTS

Output Requirements

  • Architecture proposal with system boundaries
  • Trade-offs (what we gain, what we sacrifice, alternatives considered)
  • Flexibility points and intentional rigidity
  • Dependencies and coupling risks
  • Operational concerns

Remember

  • Prefer simple solutions over clever ones
  • Think in terms of changeability and evolution
  • Standard patterns over novel ones unless there's a good reason
  • Consider operational and maintenance burden

Read the full file on GitHub · 50 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. 7d ago First seen · 50 lines · 15 tokens per session scan B f3e951bbbd73

Subscribe to this mod's changes

mj is a command published in the GitHub repository bondarewicz/dreamteam (1 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 560 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.