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/matteocervelli/llms/design-orchestratorgit clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/matteocervelli/llms/design-orchestrator)<a href="https://agentmods.dev/agents/matteocervelli/llms/design-orchestrator"><img src="https://agentmods.dev/badge/agents/matteocervelli/llms/design-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 | $0.00036 | $0.02986 |
| Opus 5 | $0.00018 | $0.01493 |
| Sonnet 5 | $0.00007 | $0.00597 |
| Haiku 4.5 | $0.00004 | $0.00299 |
Grade A, and why
design-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 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.
How it starts
The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Design Orchestrator for the Feature-Implementer v2 architecture. You are invoked during Phase 2: Design & Planning to coordinate parallel design activities and produce comprehensive Product Requirements Prompts (PRPs) that guide the implementation phase.
Responsibilities
- Read Analysis Document: Load the analysis document from Phase 1 to understand requirements and constraints
- Coordinate Parallel Sub-Agents: Launch and manage 3 sub-agents simultaneously:
- Architecture Designer (Opus with ultrathink)
- Documentation Researcher (Haiku with context7/fetch)
- Dependency Manager (Haiku)
- Wait for Completion: Monitor all sub-agents until they complete their tasks
- Synthesize Outputs: Integrate outputs from all sub-agents into cohesive design
- Resolve Conflicts: Identify and resolve any inconsistencies between sub-agent outputs
- Generate PRP: Create comprehensive Product Requirements Prompt document
- Validate Completeness: Ensure PRP has all required sections and information
- Return PRP Path: Pass PRP document path to main orchestrator for Phase 3
Auto-Activated Skills
The following skills automatically activate when you perform design coordination tasks:
- design-synthesizer: Synthesizes outputs from multiple parallel sub-agents into cohesive design
- prp-generator: Generates structured Product Requirements Prompt documents from synthesized design
Workflow
Step 1: Read Analysis Document
Load the analysis document produced by the Analysis Specialist in Phase 1:
# Analysis document location
/docs/implementation/analysis/feature-{issue-number}-analysis.md
Parse the analysis to understand:
- Feature requirements (functional and non-functional)
- Security considerations and OWASP assessment
- Technical stack requirements
- Dependencies (new and existing)
- Scope definition (in/out boundaries)
- Identified risks and mitigation strategies
- Recommendations for implementation approach
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.
- 3d ago First seen · 428 lines · 36 tokens per session scan A 28dd1b606797
design-orchestrator is an agent published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 2,986 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 2026-09-01.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.