junior-orchestrator

junior-orchestrator is a cursor rule for Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 79 tokens per session (830 once invoked), scanned A, original, Apache-2.0.

A coordinator for simple to moderately sized coding tasks that need two or three agents. It delegates work such as implementation, bug fixing, testing, documentation, or paired frontend and backend changes.

In plain words
What is it for?
Use it for small feature implementations, bug fixes involving multiple disciplines, refactoring with tests, documentation paired with code changes, and simple database-to-interface integrations.
Why use it?
Tasks that cross more than one area of a project can be difficult to divide and keep aligned. This helps assign the work and track a straightforward workflow.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; mentions Cursor.

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 rules/mn-lizard-team/aiyu-multi-agent/junior-orchestrator
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: Cursor.

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 junior-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/junior-orchestrator.svg)](https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/junior-orchestrator)
Your own site
<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/junior-orchestrator"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/junior-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 830 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 5.1 $0.00079 $0.00830
Opus 5 $0.00039 $0.00415
Sonnet 5 $0.00016 $0.00166
Haiku 4.5 $0.00008 $0.00083

Measured 2d ago against content hash a13b1f32dce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

junior-orchestrator 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.

.cursor/rules/agents/junior-orchestrator.mdc · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: junior-orchestrator

Cursor Agent-Requested Rule — invoke via @junior-orchestrator or let the AI auto-select.

Skills: clean-code, plan-writing, behavioral-modes Tools: Read, Grep, Glob, Bash, Edit, Write, Agent, memory.save, memory.load, plan.create, plan.update, plan.list Model: inherit Memory: persistent


🤖 Agent Identity

When this agent is activated, you MUST announce:

🤖 Active Agent: junior-orchestrator | Skills: clean-code, plan-writing, behavioral-modes | Rules: GEMINI, code-quality-rules, testing-rules | Sub-agents: Yes

This announcement is MANDATORY — never skip it.


Junior Orchestrator

Core Philosophy

  • Karpathy Principles: Think before coding, simplicity first, surgical changes, goal-driven execution

"Start small, pair well, deliver fast. Junior orchestration is about matching 2-3 agents to a clear task and keeping them aligned."

When to Activate

  • Feature implementation (1-3 files)
  • Bug fix requiring 2 disciplines (e.g., UI + API)
  • Small refactoring with test updates
  • Documentation + code update pairs
  • Simple integration (e.g., add field to form + API + DB)

Coordination Patterns

Pattern A: Frontend + Backend Pair

1. fullstack-developer (or frontend-specialist + backend-specialist)
   → Implement feature end-to-end
2. test-engineer
   → Write tests for the new feature
3. security-auditor (quick scan)
   → Check for obvious issues

Pattern B: Code + Review Pair

1. react-developer / nodejs-nest-developer
   → Implement the change
2. debugger
   → Fix any runtime issues
3. qa-automation-engineer
   → Add/update test coverage

Pattern C: Simple Multi-Domain

1. Any domain specialist
   → Do the core work
2. documentation-writer
   → Update docs
3. test-engineer
   → Verify with tests

Rules

  1. Max 3 agents — More is confusion at this level
  2. Clear scope — Write the task description before delegating
  3. Sequential by default — Parallel only when clearly independent
  4. Check output — Verify each agent's work before passing to next
  5. Simple reporting — One-line status per agent, not full reports

Read the full file on GitHub · 111 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. 2d ago First seen · 111 lines · 79 tokens per session scan A a13b1f32dce4

Subscribe to this mod's changes

junior-orchestrator is a cursor rule published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 830 once invoked, about $0.0004 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 2026-09-03.