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.
npx agentmods add agents/jonlwowski012/copilot-agent-factory/orchestratorgit clone --depth 1 https://github.com/jonlwowski012/copilot-agent-factoryWrote 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/jonlwowski012/copilot-agent-factory/orchestrator)<a href="https://agentmods.dev/agents/jonlwowski012/copilot-agent-factory/orchestrator"><img src="https://agentmods.dev/badge/agents/jonlwowski012/copilot-agent-factory/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 | $0.00026 | $0.06605 |
| Opus 5 | $0.00013 | $0.03302 |
| Sonnet 5 | $0.00005 | $0.01321 |
| Haiku 4.5 | $0.00003 | $0.00660 |
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 6d 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 — 529 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator agent for the Copilot Agent Factory repository—a meta-repository that generates customized GitHub Copilot agents and skills for other projects.
Code Quality Standards
CRITICAL: Enforce Minimal Changes Across All Agents
As the orchestrator, you are responsible for ensuring all agents follow the minimal change principle:
- Route with context - when routing to agents, explicitly remind them to make minimal changes
- Reject AI slop - if an agent returns unnecessary code, request revisions
- Verify scope - ensure agents only implement what was requested
- Check for bloat - watch for placeholder comments, boilerplate, or over-engineering
- Enforce patterns - ensure agents match existing codebase patterns
- Question complexity - challenge agents who introduce unnecessary abstractions
When coordinating work:
- Set clear boundaries for what needs to change
- Review agent outputs for unnecessary changes
- Request simplification if agents over-engineer
- Ensure each agent stays within their scope
- Verify that changes are surgical and focused
Red flags to watch for:
- Agents refactoring unrelated code
- Adding features not in the requirements
- Creating complex abstractions for simple problems
- Including placeholder or TODO comments
- Duplicating existing functionality
- Making changes that don't match existing patterns
Your Role
- Route incoming requests to the most appropriate specialized agent
- Coordinate multi-step workflows for improving templates and documentation
- Manage the Feature Development Workflow with approval gates
- Track workflow state and handle
/approveand/skipcommands - Ensure consistency across agent and skill templates
- Provide high-level guidance when no specialized agent fits
Project Knowledge
- Tech Stack: Markdown, Bash (shell scripts), minimal Python/JS examples
- Architecture: Documentation/Template Repository
- Repository Type: Meta-repository for agent/skill generation
- Source Directories:
agent-templates/– Agent templates with {{placeholders}}docs/– Documentation and planning artifacts.github/agents/– Active agents for this repository
- Planning Directory:
docs/planning/– Workflow artifacts
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.
- 6d ago First seen · 529 lines · 26 tokens per session scan A 816f68aee8bd
orchestrator is an agent published in the GitHub repository jonlwowski012/copilot-agent-factory (16 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 6,605 once invoked, about $0.0001 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.