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/01-gemini-protocolgit 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/01-gemini-protocol)<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/01-gemini-protocol"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/01-gemini-protocol.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 | $0.03341 | $0.03341 |
| Opus 5 | $0.01670 | $0.01670 |
| Sonnet 5 | $0.00668 | $0.00668 |
| Haiku 4.5 | $0.00334 | $0.00334 |
Grade A, and why
01-gemini-protocol 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 today.
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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md - Aiyu Agent Kit
This file defines how the AI behaves in this workspace.
🔴 MANDATORY: AGENT IDENTIFICATION (ALWAYS FIRST)
RULE ZERO: Before ANY response, you MUST announce which agent(s) are active. No exceptions. No silent work.
When to Announce
| Trigger | Action |
|---|---|
User calls /workflow |
Announce the agent that workflow activates |
| Auto-routing selects an agent | Announce the selected agent |
| Multiple agents coordinated | Announce ALL agents in the coordination |
| User asks a question | Announce the agent domain being applied |
Announcement Format (MANDATORY)
🤖 **Active Agent: `[agent-name]`** | Skills: `[skill1, skill2]` | Rules: `[rule1, rule2]` | Sub-agents: `[Yes/No]`
[Then proceed with response]
Multi-Agent Format
🤖 **Active Agents:**
- 🎯 `[primary-agent]` — Skills: `[s1, s2]` | Rules: `[r1]` — [role]
- 🔧 `[support-agent]` — Skills: `[s3, s4]` | Rules: `[r2]` — [role]
[Then proceed with response]
How to Determine Active Rules
Match rules by keywords from agent description and skills:
- Read all rule files in
.windsurf/rules/ - Check each rule's
keywords:in frontmatter - If any keyword matches the agent's description or skills → that rule is active
- Always include:
GEMINI.md(always active)
Enforcement
- ❌ VIOLATION: Responding without announcing the active agent = PROTOCOL VIOLATION
- ❌ VIOLATION: Using generic "I" without identifying which agent persona = PROTOCOL VIOLATION
- ✅ CORRECT: Every response starts with
🤖 **Active Agent:line - ✅ CORRECT: When agent changes mid-task, re-announce the new agent
🔴 Self-Check: Before hitting send, ask: "Did I announce which agent I am?" If NO → Add it.
CRITICAL: AGENT & SKILL PROTOCOL (START HERE)
MANDATORY: You MUST read the appropriate agent file and its skills BEFORE performing any implementation. This is the highest priority rule.
1. Modular Skill Loading Protocol
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.
- today First seen · 324 lines · 3,341 tokens per session scan A b796320e6052
01-gemini-protocol 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 3,341 tokens to every session, about $0.0167 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
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.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.