oh-my-githubcopilot

Plugin oh-my-githubcopilot in r3dlex/oh-my-githubcopilot. Commands read from the repo's manifest — 18 days ago.

Skills (71)

• karpathy-guidelines
• autopilot

  Autonomous end-to-end execution from idea to working code

• configure-notifications

  Configure notification integrations for Telegram, Discord, Slack

• deep-interview

  Socratic deep interview with mathematical ambiguity gating

• ecomode

  Token budget mode prioritizing task completion over exploration

• hud

  Configure HUD display options, layout, and display elements

• learner

  Extract a learned skill from the current conversation

• note

  Manage persistent notepad entries and working memory

• omp-plan

  Strategic planning mode with optional interview workflow

• omp-setup

  OMP setup wizard for directory structure and MCP configuration

• pipeline

  Sequential pipeline mode with strict phase ordering

• psm

  Plugin State Manager for OMP session state management

• ralph

  Self-referential loop until task completion with configurable verification reviewer

• release

  Automated release workflow for OMP

• swarm

  Swarm orchestration with shared state for simultaneous sub-problem solving

• swe-bench

  SWE-bench integration for running and evaluating test cases

• team

  Coordinated multi-agent session on a shared task list

• trace

  Evidence-driven tracing lane orchestrating competing tracer hypotheses

• ultrawork

  Parallel execution engine for high-throughput task completion

• wiki

  Persistent markdown knowledge base that compounds across sessions

• graph-provider
• graphify
• graphwiki
• mcp-setup
• setup
• spending
• ai-slop-cleaner

  Clean AI-generated code slop with regression-safe workflow. Activate when user says: deslop, anti-slop, AI slop, cleanup slop, clean up this code, remove bloat.

• ask

  Route multi-perspective questions through OMG's existing CCG-style analysis workflow. Activate when: ask, multi-model ask, ask models, compare model opinions.

• autoresearch

  Stateful research improvement loop with evaluator gates and decision logs. Activate when: autoresearch, research loop, improve research, evaluate research.

• cancel

  Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill it, stop everything.

• ccg

  Claude-Codex-Gemini tri-model orchestration for multi-perspective analysis. Activate when user says: ccg, tri-model, three models, multi-model, cross-validate, get multiple opinions, compare models.

• coding-standards

  Canonical cross-language coding standards reference. Shared rules embedded by reviewer agents. Activate when: viewing coding standards, checking naming rules, reviewing style baseline, consulting style guide, what are the rules.

• deep-dive

  2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive, deep-dive, investigate deeply, trace and interview.

• deepinit

  Generate or refresh hierarchical repository guidance files for agents. Activate when: deepinit, repo init docs, initialize agent docs, create AGENTS guidance.

• external-context

  Gather external documentation context through focused, bounded research passes. Activate when: external context, docs research, external docs, look up docs.

• omg-autopilot

  Full autonomous execution from idea to working code. Activate when user says: autopilot, auto-pilot, autonomous, build me, create me, make me, full auto, handle it all, or "I want a/an...

• plan

  Strategic planning with optional interview workflow. Activate when user says: plan this, plan the, let's plan, make a plan, how should we approach.

• push-omc
• ralplan

  Consensus planning with Planner/Architect/Critic iterative loop. Activate when user says: ralplan, consensus plan, consensus planning.

• remember

  Promote reusable project knowledge to the right memory surface. Activate when user says: remember this, save this, store this, remember, memorize, keep this for later.

• resume-claude
• review

  Code review with spec compliance and quality checks. Activate when user says: review this, code review, review my changes.

• sciomc

  Coordinate bounded scientist-style research analyses for data, hypotheses, and evidence. Activate when: sciomc, scientist research, research swarm, scientific analysis.

• security-scan

  Rapid security scanning workflow for code changes. Activates a focused security sweep. Activate when: security scan, scan for vulnerabilities, check for secrets, security check, run security audit, check deps.

• self-improve

  Autonomous evolutionary code improvement engine with tournament selection. Activate when user says: self-improve, self improve, evolve code, improve iteratively, tournament, benchmark loop, optimize code.

• skill-stocktake

  Audit the skill inventory for quality, coverage, and staleness. Detect overlapping, incomplete, or outdated skills and produce a health report. Activate when: skill audit, stocktake, skill inventory, check skills, which skills exist, audit skills, skill quality, skill coverage.

• skillify

  Turn a repeatable workflow into a reusable OMG skill draft. Activate when: skillify, make a skill, create skill, extract workflow.

• status

  Show current OMG mode status, active agents, and progress. Activate when user says: status, what's running, show progress, current state, active modes, where are we.

• tdd

  Test-Driven Development enforcement skill. Activates full TDD mode. Activate when: TDD, test-driven, test first, red-green-refactor, write tests first.

• ultragoal

  Durable multi-goal workflow with MCP-backed goal status, checkpoints, and completion evidence. Activate when: ultragoal, goal loop, durable goal, persistent goal, keep goal.

• ultraqa

  QA cycling workflow - test, verify, fix, repeat until goal met. Activate when user says: ultraqa, qa cycle, fix all tests, make tests pass.

• verify

  Verify that a change really works before claiming completion. Activate when user says: verify this, check if it works, prove it works.

• visual-verdict

  Structured visual QA for screenshot-to-reference comparisons. Activate when: visual verdict, screenshot compare, compare UI image, visual QA.

• writer-memory
• build-fix
• code-review
• deepsearch
• design
• doctor
• graph-context
• help
• improve-codebase-architecture
• interactive-menu
• interview
• notifications
• omp-doctor
• omp-reference
• research
• security-review
• session
• web-clone

Subagents (19)

• analyst.agent
• architect.agent
• code-reviewer.agent
• code-simplifier.agent
• critic.agent
• debugger.agent
• designer.agent
• document-specialist.agent
• executor.agent
• explore.agent
• git-master.agent
• planner.agent
• qa-tester.agent
• scientist.agent
• security-reviewer.agent
• test-engineer.agent
• tracer.agent
• verifier.agent
• writer.agent

MCP servers (1)

• oh-my-githubcopilot

  runs: node ./dist/mcp/server.mjs

Similar plugins