claude

agmo

Optimized Claude Code plugin with 8 core agents, 31 demand-loaded skills, Obsidian-centered workflow

4 on GitHubby Sungmin Chov0.9.1MITupdated 5 days ago
/

Plugin agmo from marketplace agmo-local in AGMO-Inc/agmo-everywhere. Commands read from the repo's manifest — 4 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (31)

  • accessibility

    Use to verify WCAG accessibility compliance of frontend/UI code. Auto-triggered by execute when TODO has frontend/ui tags. Triggers on "접근성", "accessibility", "WCAG".

  • benchmark

    Use to run benchmarks, save results to Obsidian vault, and detect regressions against a baseline. Triggers on "벤치마크", "benchmark", "성능 측정".

  • brainstorming

    Use when the user wants to explore an idea, design an approach, or think through a problem before implementing. Triggers on "고민", "논의", "아이디어", "brs".

  • cancel

    Use when the user wants to stop current execution. Triggers on "취소", "중단", "그만", "cancel", "stop".

  • code-review

    Use when code review is needed. Triggers on "코드 리뷰", "리뷰해줘", "code review", or at completion of implementation.

  • create-issue

    Create a GitHub Issue following org templates (Feature/Task/Bug), auto-map to GitHub Project, auto-assign current gh user, and link parent for Task issues. Triggers on "이슈 만들어", "이슈 생성", "깃허브 이슈", "create issue", "new issue", "피처 이슈", "태스크 이슈", "버그 이슈", "이슈 발행". Use this when creating issues from co

  • debt

    Use to harvest `debt:` markers across the repo into a debt ledger and optionally persist it to the Obsidian vault. Triggers on "부채", "기술부채", "debt", "지름길 정리", "/debt". Read-only — does not modify code.

  • debugging

    Use for systematic debugging. Auto-triggered when verification fails 3 times. Triggers on "디버깅", "debug", "왜 안 돼".

  • execute

    Use when the user wants to run an implementation plan. Triggers on "실행해줘", "구현해줘", "시작해줘", "execute", or after plan approval.

  • git-workflow

    Use for git operations — commit, PR, branch management. Triggers on "커밋", "commit", "PR 만들어", "브랜치".

  • handoff

    Use when the user wants to pause and leave a resume point for a later session or after /compact. Triggers on "핸드오프", "이어서 할 수 있게 정리해", "handoff", "여기까지 정리".

  • implement-page-android

    Implement an entire Figma page as Android Jetpack Compose screens by auto-splitting into frames with visual verification. Use whenever a user shares a figma.com/design URL and wants the page built as Compose code. Triggers on '안드로이드 피그마', 'Android Figma', 'Compose 구현'. Covers any multi-frame page. D

  • implement-page

    Implement an entire Figma page by auto-splitting into frames with visual verification. Use whenever a user shares a figma.com/design URL and wants the page built in code. Triggers on '피그마 구현', '피그마 페이지', 'Figma implement'. Covers any multi-frame page: landing, dashboard, marketing, etc. Does NOT app

  • note-to-issue

    Use to convert an Obsidian note into a GitHub Issue. Triggers on "노트로 이슈 만들어", "이슈로 변환", "이거 이슈로", "노트 이슈화". Only use when user explicitly references an Obsidian note as the source. For creating issues from conversation context (without a note), use create-issue instead.

  • parallel

    Use to dispatch multiple independent TODOs concurrently. Invoked by execute skill when independent TODOs are detected.

  • plan-review

    Use when a plan needs validation through a planner-critic loop. Triggers on "플랜 리뷰", "plan review", or when explicitly requested.

  • plan

    Use when the user needs a structured implementation plan with concrete TODOs. Triggers on "플랜", "계획", "plan", or after brainstorming completes.

  • plugin-review

    Use to analyze plugin usage patterns and suggest improvements. Triggers on "플러그인 리뷰", "plugin review", "사용 패턴 분석".

  • ralph

    Persistent execution loop that continues until all work is verified complete. Auto-linked by execute skill. Triggers on "끝까지 해줘", "멈추지 마", "ralph".

  • retro

    Use to generate a weekly retrospective by analyzing git log. Triggers on "회고", "retro", "이번 주 정리". Only runs on explicit user request — never auto-triggered.

  • save-impl

    Use to save implementation summary to Obsidian vault. Auto-triggered after execute completes. Triggers on "구현 저장", "작업 정리", "save impl".

  • save-note

    Use to save a design, research, meeting, or memo note to Obsidian vault. Triggers on "옵시디언에 저장", "노트 저장", "기록해줘", "정리해줘".

  • save-plan

    Fallback for when the plan skill's auto-save fails or is skipped. Use to manually save a plan to Obsidian vault. Triggers on "플랜 저장", "save plan".

  • security-audit

    Use to perform a security audit of the codebase. Triggers on "보안 점검", "security audit". Delegates to architect agent.

  • setup

    Use for first-time plugin configuration. Triggers on "setup", "설정", "초기 설정".

  • tdd

    Use when implementing with test-driven development. Triggers on "TDD", "테스트 먼저", "test first", or when the plan specifies TDD.

  • using-plugin

    Loaded automatically at session start. Teaches the orchestrator how to route requests to skills and agents. Do not invoke manually.

  • vault-search

    Use to search Obsidian vault by keyword. Triggers on "옵시디언에서 찾아", "vault 검색", "관련 노트", "이전에 작성한", "예전에 정리한".

  • verification

    Use to verify a claim of completion with evidence. Auto-triggered after each TODO in execute. Triggers on "검증", "verify", "확인해줘".

  • wiki-maintain

    Use to audit and repair the llm-wiki context spine by detecting stale, low-confidence, contested, or broken entries. Triggers on "위키 점검", "wiki maintain", "wiki audit", "컨텍스트 정리", "wiki 오염", "모순 감지".

  • wisdom

    Use to record a significant learning, decision, or issue to Obsidian vault. Triggers on "기억해", "이거 기록해", "wisdom", or when a significant learning occurs during debugging/verification.

Subagents (8)

  • android-specialist

    Android frontend quality gate agent with 3 verification modes: visual (Figma vs Compose Preview comparison), accessibility (Android WCAG review), responsive (multi-screen-size verification).

  • architect

    Use this agent for analysis, verification, debugging, and architectural decisions. Examples: <example>Verify that all tests pass and the build is clean</example> <example>Debug why the API returns 500 on this endpoint</example> <example>Analyze the impact of changing the database schema</example> <e

  • archivist

    Use this agent for all Obsidian vault operations — saving, searching, updating, and managing notes. Examples: <example>Save an implementation summary to Obsidian vault</example> <example>Search Obsidian vault for related notes</example> <example>Update an existing note with additional content</examp

  • critic

    Use this agent for reviewing plans, code, and providing structured critique. Examples: <example>Review this implementation plan for completeness and risks</example> <example>Check if this code matches the specification</example> <example>Evaluate whether the refactoring preserved all behavior</examp

  • executor

    Use this agent for all code implementation and modification tasks. Examples: <example>Implement a new API endpoint based on the plan</example> <example>Fix a bug in the authentication module</example> <example>Write a migration script</example>

  • explore

    Use this agent for codebase search, file discovery, and information gathering. Examples: <example>Find all files that import the UserService class</example> <example>Search for how authentication is implemented</example> <example>List all API endpoints in the project</example>

  • frontend

    Frontend quality gate agent with 3 verification modes: visual (Figma vs browser comparison), accessibility (WCAG static review), responsive (multi-breakpoint verification). Examples: <example>Compare Figma screenshot against browser screenshot and return VERDICT/SCORE/ISSUES</example> <example>Run W

  • planner

    Use this agent for creating plans, breaking down tasks, and strategic thinking. Examples: <example>Create an implementation plan for the new authentication system</example> <example>Break down this feature request into concrete TODOs</example> <example>Design the API structure for the order manageme

Hooks (7)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/session-start"

  • UserPromptSubmit

    ${CLAUDE_PLUGIN_ROOT}/hooks/hud-slash-detect

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/guard"

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/hud-skill-update"

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/hooks/post-tool-reminder"

  • SubagentStart

    "${CLAUDE_PLUGIN_ROOT}/hooks/hud-agent-start"

  • SubagentStop

    "${CLAUDE_PLUGIN_ROOT}/hooks/hud-agent-stop"

View source on GitHub

Maintain agmo?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted