enhance

enhance is a command for Claude Code, Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 0 tokens per session (488 once invoked), scanned A, original, Apache-2.0.

A command specification for updating an existing application with new features. It requires an agent activation line, clarification when requirements are unclear, project-state checks, and a completion report.

In plain words
What is it for?
Use it when enhancing an existing application rather than starting a new one, such as adding features or changing current behavior.
Why use it?
It gives the agent a fixed process for understanding the current application before making changes and for reporting what happened afterward.

Command for Claude CodeCursor

Written for Claude Code and Cursor: $ARGUMENTS substitution, but also installed under .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 commands/mn-lizard-team/aiyu-multi-agent/enhance
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: Claude Code, 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 enhance

README.md
[![agentmods](https://agentmods.dev/badge/commands/mn-lizard-team/aiyu-multi-agent/enhance.svg)](https://agentmods.dev/commands/mn-lizard-team/aiyu-multi-agent/enhance)
Your own site
<a href="https://agentmods.dev/commands/mn-lizard-team/aiyu-multi-agent/enhance"><img src="https://agentmods.dev/badge/commands/mn-lizard-team/aiyu-multi-agent/enhance.svg" alt="Measured on agentmods" height="20"></a>
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 488 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 $0.00000 $0.00488
Opus 5 $0.00000 $0.00244
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 6d ago against content hash c73e1b6777f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

enhance 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 6d 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/commands/enhance.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/enhance

Add or update features in existing application. Used for iterative development.


⚠️ CURSOR OUTPUT CONTRACT

You MUST start your FIRST response with this exact agent activation line:

🤖 **Active Agent: `orchestrator`** | Skills: `clean-code, parallel-agents, behavioral-modes, plan-writing +5 more`

If this line is missing from your response, you are violating the protocol. Add it before any other content.

Required Behavior

  1. Follow the task steps defined below
  2. Apply the Socratic Gate: ask clarifying questions if requirements are unclear
  3. Report completion status at the end

/enhance - Update Application

$ARGUMENTS


🤖 Agent Activation

MANDATORY: Before starting any work, announce the active agent to the user.

🤖 **Active Agent: `orchestrator`** | Skills: `clean-code, parallel-agents, behavioral-modes, plan-writing +5 more`

Task

This command adds features or makes updates to existing application. Activated by code-archaeologist, frontend-specialist, and backend-specialist agents.

Steps:

  1. Understand Current State

    • Load project state with python3 .windsurf/scripts/session_manager.py info
    • Understand existing features, tech stack
  2. Plan Changes

    • Determine what will be added/changed
    • Detect affected files
    • Check dependencies
  3. Present Plan to User (for major changes)

    "To add admin panel:
    - I'll create 15 new files
    - Update 8 files
    - Takes ~10 minutes
    
    Should I start?"
    
  4. Apply

    • Call relevant agents
    • Make changes
    • Test
  5. Update Preview

    • Hot reload or restart

Usage Examples

/enhance add dark mode
/enhance build admin panel
/enhance integrate payment system
/enhance add search feature
/enhance edit profile page
/enhance make responsive

Caution

  • Get approval for major changes
  • Warn on conflicting requests (e.g., "use Firebase" when project uses PostgreSQL)
  • Commit each change with git

Read the full file on GitHub · 93 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. 6d ago First seen · 93 lines · 0 tokens per session scan A c73e1b6777f5

Subscribe to this mod's changes

enhance is a command published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 488 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 2026-08-31.