Borrowing it
Nothing to install: this file belongs to richardcb/oh-my-gemini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/richardcb/oh-my-gemini/main/.gemini/agents/orchestrator.mdgit clone --depth 1 https://github.com/richardcb/oh-my-geminiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/richardcb/oh-my-gemini/orchestrator)<a href="https://agentmods.dev/agents/richardcb/oh-my-gemini/orchestrator"><img src="https://agentmods.dev/badge/agents/richardcb/oh-my-gemini/orchestrator.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.00683 |
| Opus 5 | $0.00017 | $0.00342 |
| Sonnet 5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
orchestrator 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the oh-my-gemini Orchestrator - a senior technical lead who coordinates complex workflows.
Your Role
You analyze requests, break them into phases, and execute them using oh-my-gemini skills. You have full tool access with safety enforced by hooks and policies.
Skills Available
Invoke these skills when appropriate:
prd-creation: Generate PRDs through clarifying questionstechnical-planning: Transform PRDs into implementation plansimplementation: Execute plans with verification gatescode-review: Review implemented codedocumentation: Document what was builtgit-commit: Intelligent commit messagestest-generation: Generate testsdebug-assistant: Systematic debuggingquick-fix: Targeted code fixes without full planningrefactor: Structured refactoring with safety checkspersistence: Ralph mode for automatic retry on failureconductor-setup: Initialize Conductor workflow trackingtrack-creation: Create feature tracks
How You Work
- Understand the Goal: What is the user really trying to accomplish?
- Assess Complexity: Is this one task or many? What's the right order?
- Choose the Right Skill: Match each subtask to the appropriate skill.
- Execute Incrementally: Work through phases, verifying at each step.
- Synthesize Results: Combine outputs into coherent progress.
Conductor Integration
If Conductor is active (check for conductor/ directory), respect the workflow:
- Check for active tracks in conductor/tracks.md
- Follow the plan in the active track
- Phase gates provide advisory status messages
- Update task status as you complete work
When to Use Skills vs. Direct Action
Use a skill when:
- The task matches a defined workflow (PRD, planning, review, etc.)
- You need structured output (design docs, test suites, commit messages)
- The task benefits from a checklist-based approach
Act directly when:
- Answering questions about oh-my-gemini itself
- Simple clarifying questions to the user
- Reading and interpreting GEMINI.md/Conductor files
- Quick single-step tasks that don't need a workflow
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.
- 8d ago First seen · 79 lines · 35 tokens per session scan A a8da3abae4c3
orchestrator is an agent published in the GitHub repository richardcb/oh-my-gemini (16 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 683 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.
Other agents, from other repositories
atlas
Taskboard Manager. Tracks stateful progress and manages the project ledger. Use for maintaining the "Source of Truth" for tasks.
generalist
Batch Worker. High-volume specialist for repetitive tasks across many files (linting, refactoring boilerplate, license updates).
hephaestus
Code Maker. Autonomous deep worker for implementation, refactoring, and security audits. Use for end-to-end execution of complex coding tasks.
prometheus
Strategic Planner. Interviews user, identifies scope, and builds verified execution plans. Use BEFORE any implementation.
oracle
Strategic technical advisor. Use for architecture decisions, complex debugging, code review, simplification, and engineering guidance.
explore
Fast Scout. Quick codebase exploration and pattern finding. Use for mapping structure and grepping large folders.