By code-yeongyu
One Claude Code plugin namespace for Yeongyu's local Claude Code components.
Codebase search specialist. Use proactively when you need to find files or code in the working tree and want absolute paths with structured results — especially when multiple search angles are needed or the module structure is unfamiliar. Read-only.
External open-source codebase and documentation researcher. Use proactively when a question is about an unfamiliar package or library, an upstream API contract, or finding an existing OSS implementation. Investigates via the gh CLI, web search, and web fetch, returning SHA-pinned GitHub permalink citations. Read-only.
Pre-planning analyst. Use proactively before the planner commits to a draft plan or vague request: detects contradictions, ambiguity, missing constraints, and execution risks so the planner can patch the plan in one pass. Read-only.
Plan reviewer. Use proactively after a work plan is drafted to verify it is executable: referenced files exist, tasks are startable, and QA scenarios are concrete. Issues OKAY, ITERATE, or REJECT. Read-only.
Strategic planning consultant. Use proactively when a request is vague or large (5+ interdependent steps, ambiguous scope, multiple files/modules involved) and you need a single executable work plan before any implementation. Planner only — never implements. Writes the plan to `plans/<slug>.md`.
Removes AI-generated code smells from a SINGLE file while preserving functionality. For multiple files, call in PARALLEL per file.
Use when Codex needs to understand or respond to automatic comment-checker feedback emitted after an edit-like PostToolUse hook.
MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles from orthogonal angles, confirm root cause, lock with a failing test, fix minimally, QA by actually USING the system, scrub artifacts. The actual HOW lives in `references/` — READ THEM. Triggers: 'debug this', 'why is X not working', 'hanging', 'attach a debugger', 'reverse engineer', 'pwndbg', 'gdb', 'lldb', 'node inspect', 'tsx debug', 'pdb', 'dlv', 'delve', 'rust-gdb', 'set a breakpoint', 'context window exploded', 'why is the response empty', 'attach the debugger', 'debug it', 'why is this happening', 'trace this bug', 'reproduce and fix', 'silent failure', 'HTTP 200 but empty', 'why did it stop', 'inspect the binary', 'reverse engineering', 'playwright'.
Designer-turned-developer who crafts stunning UI/UX even without design mockups
(builtin) Initialize hierarchical AGENTS.md knowledge base
Admin access level
Server config contains admin-level keywords
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
The lazy way to run omo inside Claude Code. A native Claude Code plugin marketplace by Sisyphus Labs.
What it is · Install · Components · MCP · Telemetry · omo
omo for Claude Code brings the omo experience — rule injection, comment checking, LSP intelligence, ultrawork orchestration, durable ultragoal tracking, and start-work continuation — into Claude Code through Claude Code's native plugin system.
This repository is the distribution surface: a native Claude Code plugin
marketplace. The marketplace is named sisyphuslabs and ships a single
plugin named omo. The repository name (lazyclaudecode) is the install
alias and the home of this marketplace — it is not the marketplace name.
The marketplace name is
sisyphuslabs. The plugin name isomo. You install the plugin asomo@sisyphuslabs.
Everything is self-contained: hooks, skills, subagents, and the bundled MCP
servers all resolve from ${CLAUDE_PLUGIN_ROOT}, so the plugin runs correctly
straight from the Claude Code plugin cache.
Add this marketplace, then install the omo plugin:
/plugin marketplace add code-yeongyu/lazyclaudecode
/plugin install omo@sisyphuslabs
# Claude Code platform (cc is the short alias for claudecode):
bunx omo install --platform=cc
# or via the dedicated alias (same compiled CLI, defaults to Claude Code):
bunx lazyclaudecode install
The omo CLI shells out to claude plugin marketplace add code-yeongyu/lazyclaudecode
and claude plugin install omo@sisyphuslabs. If claude is not on your PATH,
it prints the two /plugin commands above so you can run them inside a Claude
Code session.
omo is one plugin namespace; each capability stays isolated internally as a
component.
| Component | What it does |
|---|---|
| rules | Injects AGENTS.md / CLAUDE.md / .omo/rules/** into context via SessionStart, UserPromptSubmit, PostToolUse, and PostCompact. |
| comment-checker | Runs comment-checker after Write / Edit / MultiEdit tool use to keep comments honest. |
| lsp | Exposes Language Server Protocol diagnostics, navigation, symbols, and rename through MCP plus post-edit hooks. |
| ultrawork | Detects ultrawork / ulw in a prompt and injects the full ultrawork orchestration directive. |
| ultragoal | Durable, repo-native multi-goal orchestration with embedded success criteria and an observable evidence audit under .omo/ultragoal/, scoped per Claude Code session. |
| start-work-continuation | A Stop / SubagentStop continuation hook that resumes .omo/boulder.json start-work plans, keyed per Claude Code session. |
| telemetry | Anonymous, opt-out daily-active signal emitted on the plugin SessionStart hook. |
omo bundles two MCP servers, wired through ${CLAUDE_PLUGIN_ROOT} so they
spawn cleanly from the plugin cache:
| Server | Purpose |
|---|---|
| ast_grep | Structural code search and rewrite via ast-grep. |
| lsp | Language Server Protocol tools: diagnostics, definitions, references, symbols, rename. |
Installing omo registers a library of skills (init-deep, planning,
refactor, remove-ai-slops, review-work, start-work, and more) and a set of
subagents for orchestrated work:
| Subagent | Role | Model |
|---|---|---|
| reviewer | Reviews ultrawork output against the directive. | opus |
| metis | Strategic planning and decomposition. | opus |
| planner | Turns objectives into executable plans. | opus |
| momus | Adversarial critique of plans and changes. | opus |
| explorer | Fast, read-only codebase reconnaissance. | haiku |
| librarian | Fast, read-only documentation and reference lookup. | haiku |
Skills carry a Claude Code Harness Tool Compatibility section so they speak in
Claude Code's native verbs (Edit, Write, MultiEdit, Task).
Opinionated basic Claude Code setup with intelligent context injection, language-specific guides, project knowledge, and encoding validation
Web development tools with Playwright browser automation via MCP
npx claudepluginhub code-yeongyu/lazyclaudecode --plugin omoMemory compression system for Claude Code - persist context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns