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 rules/mn-lizard-team/aiyu-multi-agent/junior-orchestratorgit clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agentWrote 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/rules/mn-lizard-team/aiyu-multi-agent/junior-orchestrator)<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>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 5.1 | $0.00079 | $0.00830 |
| Opus 5 | $0.00039 | $0.00415 |
| Sonnet 5 | $0.00016 | $0.00166 |
| Haiku 4.5 | $0.00008 | $0.00083 |
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.
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-orchestratoror 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
- Max 3 agents — More is confusion at this level
- Clear scope — Write the task description before delegating
- Sequential by default — Parallel only when clearly independent
- Check output — Verify each agent's work before passing to next
- Simple reporting — One-line status per agent, not full reports
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.
- 2d ago First seen · 111 lines · 79 tokens per session scan A a13b1f32dce4
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.