claude

og

Portable orchestrator: generic agents, skills, guard hooks, and /og:orchestrate + /og:orchestrate-init slash commands for any repo.

0 on GitHubby George Louthanv0.4.1updated 3 months agoworkflow
/

Plugin og from marketplace duplico in duplico/claude-og-plugin. Commands read from the repo's manifest — 1 month 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 (8)

  • check-wsl

    Run the og-check-wsl diagnostic: probe the WSL2/Windows interop surface (notify-send, WSLg, PowerShell, BurntToast, cmd.exe, clip.exe, sshd) and report which path the plugin's notify hook will use. Pass --test-notify to actually fire a desktop toast.

  • closed-loop-helpers

    Closed-loop PR review protocol and helper scripts. Preloaded by the closed-loop-runner agent.

  • copilot-reviews

    How to trigger and correctly find GitHub Copilot code reviews on a PR. Opt-in -- load only when the user brings Copilot into the review cycle.

  • orchestrate-init

    Bootstrap a repository's Claude Code setup: investigate the stack, then generate a project orchestrator overlay, CLAUDE.md, permissions, optional domain agents, and gitignore entries. Run once per repo to get from zero to a useful, familiar orchestration setup.

  • orchestrate

    Become the orchestrator for the current repository: scan repo + available subagents, check GitHub state, then coordinate and delegate work. Use when the user wants to coordinate multi-step or multi-repo work, dispatch subagents, run a review/fix loop, or asks to 'orchestrate' / 'coordinate' a task.

  • pr-response-protocol

    Protocol for responding to PR review comments. Preloaded by developer agents.

  • refresh

    Reconcile an existing repo's og setup with the current plugin: check plugin freshness, find duplicated generics, migrate legacy numbered rules to the namespaced scheme, lint for anti-patterns, and fact-check the overlay against the actual repo. Report-first; nothing changes without confirmation.

  • sync

    Apply plugin updates down into this project's .claude/ overlay and agents. Fixes bare references to plugin agents/skills that should be og:-prefixed, and inserts shared-utility rows missing from the overlay's agent table. Run after a plugin update or whenever the project files have drifted from the

Subagents (7)

  • closed-loop-runner

    Runs a closed-loop session for an issue or PR. Handles the full lifecycle: PR creation, CI monitoring, review polling, and review-fix cycles until completion or escalation. Repo- and stack-agnostic.\n\nExamples:\n\n<example>\nContext: Orchestrator dispatching for an issue (no PR yet).\nassistant: \"

  • editor

    Use this agent to verify formatting, linting, or style compliance for any code, configuration, or documentation. This includes: reviewing code for style consistency before committing, resolving questions about proper formatting in a specific context, evaluating whether existing lint rule exclusions

  • just-expert

    Use this agent when working with justfiles, creating new recipes, refactoring existing just configurations, or when questions arise about just syntax and best practices. This agent should be used proactively whenever justfile modifications are being made or when organizing build/task automation. Exa

  • orchestrator-developer

    Use this agent to implement features, fix bugs, or address issues/PR comments in any repository. It creates an isolated git worktree, works independently, commits incrementally, and opens or updates a PR. Stack-agnostic: detects the project's build/test tooling. Preloads the PR response protocol.\n\

  • orchestrator-reviewer

    Use this agent for adversarial code review before commit or merge, convention-adherence checks, and triage of incoming PR review comments. Provides fresh, skeptical eyes and verifies the issue→PR→code chain. Stack-agnostic.\n\nExamples:\n\n<example>\nContext: Changes are ready for review before comm

  • orchestrator-tester

    Use this agent to write tests, run the project's test suite, investigate flaky or failing tests, and validate behavior end-to-end. Stack-agnostic: detects the test runner and conventions. Use it to add coverage for a new feature or to diagnose a CI failure.\n\nExamples:\n\n<example>\nContext: A new

  • web-doc-searcher

    Use this agent to look up documentation for tools, libraries, or APIs that may be newer than your knowledge cutoff or are less commonly documented. Use it when you encounter an unfamiliar tool, need to verify current syntax/behavior, or when the user explicitly asks about documentation for an extern

Hooks (5)

  • PreToolUse

    python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/git_branch_guard.py

  • PreToolUse

    python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/github_disclosure.py

  • PreToolUse

    python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/worktree_cleanup_guard.py

  • PreToolUse

    python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/worktree_guard.py

  • Notification

    python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/notify_wsl.py

View source on GitHub

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

beads

claudecodex

AI-supervised issue tracker for coding workflows

1 skill · 1 agent · hooks

gastownhall/beads 28,698

MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows

18 skills

MiniMax-AI/skills 13,828

worktrunk

claudecodex

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.

2 skills · hooks

max-sixty/worktrunk 12,481

gsd-core

claude

GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.

72 skills · 72 commands · 64 agents · hooks

open-gsd/gsd-core 11,494

Maintain og?

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