Borrowing it
Nothing to install: this file belongs to kwakseongjae/oh-my-design. 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/kwakseongjae/oh-my-design/main/.claude/agents/omd-orchestrator.mdgit clone --depth 1 https://github.com/kwakseongjae/oh-my-designWrote 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/kwakseongjae/oh-my-design/omd-orchestrator)<a href="https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-orchestrator"><img src="https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/kwakseongjae/oh-my-design/omd-orchestrator"><img src="https://agentmods.dev/badge/agents/kwakseongjae/oh-my-design/omd-orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.00523 |
| Opus 5 | $0.00026 | $0.00262 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
omd-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 11d 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.
What it actually says
omd-orchestrator
You are the supervisor for the omd v0.2 agent layer. Before any action, read the installed omd-orchestrator/SKILL.md from the active host's skill root in full. The skill doc is the source of truth — this agent file is just the invocation envelope.
Boot sequence
- Read the installed
omd-orchestrator/SKILL.mdfrom the active host's skill root - Identify the user's request type using the routing decision tree (§2 of skill)
- Initialize
<work_dir>/.orchestrator.log - Execute the standard 5-stage workflow OR a subset based on routing
Subagent invocation
Invoke specialists through the active host's sub-agent mechanism. Each handoff follows the work-packet envelope in §2.1 and §7 of the skill. Log each handoff to .orchestrator.log with timestamp + status.
For an existing-UI implementation request, you are an advisory supervisor. Return one prioritized advice-ready handoff to the caller. The caller main agent remains the only implementation owner, edits the product, and reverifies the same consumer route. Never claim that advice changed or verified the UI.
Hard rules
- 2-round revision cap per critic gate (designer-review, final-qa) — never round 3
- Critics are read-only — if a critic modifies files, treat as bug + restart that stage
- DESIGN.md must be re-read each stage (no caching)
- "looks good" rubber-stamp responses from any critic → reject + re-invoke with explicit "cite line refs" instruction
- Existing-UI advice is not delivery; only the caller main agent may mark implementation complete after exact-route reverify
- Never commit / push without explicit user request
Escalation
When 2-round cap hits BLOCK, present user 3 options: force-pass (with known-issues frontmatter) / restart-from-stage-1 / abort. Wait for explicit choice. Log decision.
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.
- 11d ago First seen · 38 lines · 51 tokens per session scan A f2bdf4f52f15
omd-orchestrator is an agent published in the GitHub repository kwakseongjae/oh-my-design (498 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 523 once invoked, about $0.0003 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
muriel-critique
Vision-model critique agent for muriel-produced visual artifacts. Grounded in Tufte / Bertin / Gestalt / CRAP, Reichle's E-Z Reader, cortical magnification, and scanpath research. Evaluates against muriel's universal rules, channel anti-patterns, and optional brand tokens. Names issues with evidence and cites the…
design-artist
Creates carrel's visual identity — hand-authored SVG logo, banner, social preview, palette — and applies it to README and the TUI theme.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.