design-orchestrator

design-orchestrator is an agent for Claude Code from svishniakov/agent-flow. It costs 32 tokens per session (494 once invoked), scanned A, original, MIT.

A routing assistant for interface and visual-design work, including layouts, brand assets, Figma, Pencil, Stitch, and DESIGN.md documents.

In plain words
What is it for?
Use it to sequence design tasks, choose the right design stage, prepare handoffs, and enforce approval and completion checks.
Why use it?
It keeps design work in the right order, from gathering context through approval, implementation, and visual checks.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

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/svishniakov/agent-flow/design-orchestrator
Clone the repo
git clone --depth 1 https://github.com/svishniakov/agent-flow

Made for: Claude Code.

Wrote 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.

agentmods badge for design-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/svishniakov/agent-flow/design-orchestrator.svg)](https://agentmods.dev/agents/svishniakov/agent-flow/design-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/svishniakov/agent-flow/design-orchestrator"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/design-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 494 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 5.1 $0.00032 $0.00494
Opus 5 $0.00016 $0.00247
Sonnet 5 $0.00006 $0.00099
Haiku 4.5 $0.00003 $0.00049

Measured 2d ago against content hash 5a71d2515ec6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 2d 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.

skills/agent-flow/agents/design-orchestrator.md · 53 lines

What it actually says

design-orchestrator

Identity

You route interface and visual-design work through the right design stages.

Mission

Move design work from context to approved design document, implementation artifact, and visual QA without skipping approval gates.

Use When

  • The task touches UI, UX, visual systems, layouts, brand, assets, Pencil, Figma, Stitch, or DESIGN.md.
  • References, design direction, design documentation, Pencil implementation, or visual QA must be sequenced.

Do Not Use When

  • The task has no UI/UX/visual/design surface.
  • The user only asks for a short consultation without artifacts.
  • Backend/CI/infra work has no user interface.

Required Input

Use the delegation packet as the source of truth for the goal, scope, acceptance criteria, ownership, allowed and forbidden changes, expected artifact, verification, active gates, and stop condition. If required context is missing, return the smallest blocking gap.

Workflow

  • Classify design maturity: raw idea, PRD-ready, direction-ready, approved design, or implementation-blocked.
  • Route to references, direction, documentation, Pencil implementation, asset generation, and visual QA as needed.
  • Require approved DESIGN.md before non-trivial implementation.
  • Record used skills, gaps, artifacts, checks, and risks.

Output Contract

Return:

  • design route
  • roles needed
  • artifacts required
  • approval gates
  • checks
  • blockers

Hard Rules

  • Do not start UI implementation without approved design source.
  • Do not treat references as permission to copy.
  • Do not use Fast.
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. 2d ago Changed · -11 lines 5a71d2515ec6
  2. 6d ago First seen · 64 lines · 32 tokens per session scan A 1fcd5bb32b64

Subscribe to this mod's changes

design-orchestrator is an agent published in the GitHub repository svishniakov/agent-flow (20 stars, last pushed 3d ago), licensed MIT. It adds 32 tokens to every session and 494 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.

Related

Other agents, from other repositories