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.
/plugin marketplace add code-yeongyu/lazyclaudecodenpx agentmods add plugins/code-yeongyu/lazyclaudecode/omogit clone --depth 1 https://github.com/code-yeongyu/lazyclaudecodeGrade A, and why
omo 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 yesterday.
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.
What it actually says
{
"name": "omo",
"version": "0.1.0",
"description": "One Claude Code plugin namespace for Yeongyu's local Claude Code components.",
"author": {
"name": "Yeongyu Kim",
"email": "[email protected]",
"url": "https://github.com/code-yeongyu"
},
"homepage": "https://github.com/code-yeongyu/lazyclaudecode",
"repository": "https://github.com/code-yeongyu/lazyclaudecode",
"license": "MIT",
"keywords": ["claude-code", "claude-code-plugin", "omo", "hooks", "mcp", "skills"],
"skills": "./skills/",
"hooks": "./hooks/hooks.json",
"mcpServers": "./.mcp.json",
"interface": {
"displayName": "OMO",
"shortDescription": "Unified local Claude Code components",
"longDescription": "OMO exposes the local Claude Code Rules, Comment Checker, LSP, Ultrawork, and Ultragoal components as one plugin namespace while keeping each component isolated under components/ for maintenance.",
"developerName": "Yeongyu Kim",
"category": "Developer Tools",
"capabilities": ["Hooks", "MCP Tools", "Code Intelligence", "Workflow", "Context Injection"],
"websiteURL": "https://github.com/code-yeongyu/lazyclaudecode",
"privacyPolicyURL": "https://github.com/code-yeongyu/lazyclaudecode#privacy",
"termsOfServiceURL": "https://github.com/code-yeongyu/lazyclaudecode#license",
"defaultPrompt": [
"Use OMO LSP diagnostics on this workspace.",
"Show which OMO rules matched this file.",
"ulw: run this change with evidence."
],
"brandColor": "#D97757",
"screenshots": []
}
}
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.
- yesterday First seen · 36 lines scan A ea241abb9cd6
omo is a plugin published in the GitHub repository code-yeongyu/lazyclaudecode (18 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
probity
Plugin marketplace listing 1 plugin: probity.
ballast
Builds up to a goal in a field you have no expertise in — learns the foundations it needs and keeps every solved path for the next goal.
makoto
Plugin marketplace listing 1 plugin: makoto.
hush
Trims command output, logs, and Claude's play-by-play before they pile up in the session, so long, noisy work stays quiet and readable. Install and forget — nothing to configure. Short questions with nothing to run cost a little more.
claude-code-message-timestamps
Shows the local time on every message and tells Claude when each prompt was sent — so you can scan a conversation, see how long things took, and reference earlier blocks.
nunchi-marketplace
JIT rule-delivery plugin — compiles CLAUDE.md rules into trigger-bound hooks.