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 commands/mn-lizard-team/aiyu-multi-agent/delphigit 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/commands/mn-lizard-team/aiyu-multi-agent/delphi)<a href="https://agentmods.dev/commands/mn-lizard-team/aiyu-multi-agent/delphi"><img src="https://agentmods.dev/badge/commands/mn-lizard-team/aiyu-multi-agent/delphi.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 | $0.00000 | $0.00605 |
| Opus 5 | $0.00000 | $0.00302 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
delphi 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- electric — 86% identical, 72 lines differ
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/delphi
Delphi and Pascal development — VCL, FireMonkey, FireDAC, legacy modernization, and Object Pascal best practices. Used for Windows desktop apps, cross-platform UI, or maintaining legacy Delphi codebases.
⚠️ CURSOR OUTPUT CONTRACT
You MUST start your FIRST response with this exact agent activation line:
🤖 **Active Agent: `delphi-developer`** | Skills: `clean-code, delphi-pascal, database-design, api-patterns +1 more`
If this line is missing from your response, you are violating the protocol. Add it before any other content.
Required Behavior
- Read the agent's full instructions from
.windsurf/agents/delphi-developer.md(or.cursor/rules/agents/delphi-developer.mdc) - Apply the Socratic Gate: ask clarifying questions before coding if requirements are unclear
- Follow clean-code principles: concise, no over-engineering, self-documenting
/delphi — Delphi & Pascal Development
$ARGUMENTS
🤖 Agent Activation
MANDATORY: Before starting any work, announce the active agent to the user.
🤖 **Active Agent: `delphi-developer`** | Skills: `clean-code, delphi-pascal, database-design, api-patterns +1 more`
Task
Build, maintain, or modernize Delphi/Pascal applications.
Steps:
-
Project Assessment
- Identify Delphi version and framework (VCL/FMX/RTL)
- Check existing component dependencies
- Assess legacy patterns (BDE, global state, with-statements)
-
Architecture Design
- Layered: UI → Business Logic → Data Access → Database
- DataModules for data access
- Frames for reusable UI blocks
- Dependency injection (Spring4D)
-
Implementation
- Follow naming conventions (T prefix, F fields, A params)
- RAII / try-finally for memory management
- FireDAC for database access
- DUnitX for testing
-
Legacy Modernization (if applicable)
- BDE → FireDAC migration
- Global variables → DI
- God forms → Frames + Services
- StringList → JSON
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.
- 4d ago First seen · 90 lines · 0 tokens per session scan A 6331eb47594f
delphi 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 605 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.
Other commands, from other repositories
nav-graph
Extract, inspect, and query the app navigation graph — a complete map of all screens and navigators.
rn-feature-dev
Guided feature development for React Native — explore codebase, design architecture, implement, verify live on device, and review quality.
brainstorm
Command dispatcher for brainstorm.
plan
Command dispatcher for plan.
goal
Open a /goal contract — write a verifiable manifest before dispatching work.
qos-workspace
Browse the workspace files and agent logs of a completed QOS task.