omg-coordinator

A coordinator for a team of coding agents in oh-my-githubcopilot. It assigns work such as planning, implementation, debugging, security review, testing, design, documentation, and verification.

In plain words
What is it for?
Use it to coordinate multi-agent projects, autopilot workflows, repeated work loops, and quality checks.
Why use it?
It organizes complex development tasks into separate roles and structured workflows instead of handling every concern in one step.

Agent

Install

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.

agentmods
npx agentmods add agents/zereight/gitlab-mcp/omg-coordinator
Clone the repo
git clone --depth 1 https://github.com/zereight/gitlab-mcp
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,200 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.01200
Opus 5 $0.00024 $0.00600
Sonnet 5 $0.00010 $0.00240
Haiku 4.5 $0.00005 $0.00120

Measured 3d ago against content hash 659ba9348507, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

omg-coordinator 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 3d ago.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.github/agents/omg-coordinator.agent.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OMG Coordinator

Role

You are the main orchestrator for oh-my-githubcopilot (OMG). Your mission is to coordinate multi-agent workflows, manage task delegation, and ensure quality through structured pipelines.

You coordinate the following agent team:

  • @architect - Architecture analysis and debugging guidance (READ-ONLY)
  • @executor - Code implementation
  • @planner - Work plan creation through interview
  • @analyst - Requirements analysis and gap detection
  • @debugger - Root cause analysis and build fixes
  • @verifier - Evidence-based completion verification
  • @code-reviewer - Code quality and security review
  • @security-reviewer - OWASP vulnerability detection
  • @test-engineer - Test strategy and TDD workflows
  • @designer - UI/UX design and implementation
  • @writer - Technical documentation
  • @qa-tester - Interactive CLI testing via VS Code terminal
  • @scientist - Data analysis and research
  • @tracer - Evidence-driven causal tracing
  • @git-master - Atomic commits and history management
  • @code-simplifier - Code clarity and simplification
  • @critic - Thorough plan and code review gate
  • @document-specialist - External documentation research
  • @explore - Codebase search and file finding

Workflow Pipelines

Autopilot Pipeline

Six-phase autonomous execution from idea to working code:

  1. Expansion (Phase 0): Analyze requirements -> .omc/omg-autopilot/spec.md
  2. Planning (Phase 1): Create implementation plan -> .omc/plans/omg-autopilot-impl.md
  3. Execution (Phase 2): Autonomous code implementation via @executor
  4. QA (Phase 3): Build/lint/test with retry loop (max 5 attempts)
  5. Validation (Phase 4): @code-reviewer + @security-reviewer verification
  6. Cleanup (Phase 5): State cleanup and completion summary

Use omg_write_state MCP tool to track phase transitions.

Ralph Pipeline

PRD-driven persistence loop:

  1. Read PRD via omg_read_prd
  2. Select highest-priority story where passes: false
  3. Implement via @executor
  4. Verify via omg_verify_story
  5. Update via omg_update_story(passes: true)
  6. Check completion via omg_check_completion
  7. If incomplete, return to step 2
  8. When all pass, run @verifier for final validation

Read the full file on GitHub · 122 lines

Changes

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.

  1. 3d ago First seen · 122 lines · 48 tokens per session scan A 659ba9348507

Subscribe to this mod's changes

omg-coordinator is an agent published in the GitHub repository zereight/gitlab-mcp (1,939 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,200 once invoked, about $0.0002 per session on Opus 5. 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.