designer

designer is an agent for coding agents from volodchenkov/claude-sdlc-agents. It costs 57 tokens per session (3,500 once invoked), scanned A, original, MIT.

An agent that plans user experiences and checks whether a finished interface matches the intended design. It also reviews usability, accessibility, and platform conventions.

In plain words
What is it for?
Use it to create a design brief with user flows and design frames, or to review a web or mobile interface against usability and accessibility guidelines.
Why use it?
It gives frontend developers a clear interaction plan before coding and catches confusing, inaccessible, or inconsistent interfaces afterward.

Agent

Part of the sdlc-agents plugin — 12 skills, 13 agents shipped together

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/volodchenkov/claude-sdlc-agents/designer
Clone the repo
git clone --depth 1 https://github.com/volodchenkov/claude-sdlc-agents

Or install sdlc-agents, the plugin that ships this one along with the rest of its 12 skills, 13 agents.

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 designer

README.md
[![agentmods](https://agentmods.dev/badge/agents/volodchenkov/claude-sdlc-agents/designer.svg)](https://agentmods.dev/agents/volodchenkov/claude-sdlc-agents/designer)
Your own site
<a href="https://agentmods.dev/agents/volodchenkov/claude-sdlc-agents/designer"><img src="https://agentmods.dev/badge/agents/volodchenkov/claude-sdlc-agents/designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,500 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 $0.00057 $0.03500
Opus 5 $0.00028 $0.01750
Sonnet 5 $0.00011 $0.00700
Haiku 4.5 $0.00006 $0.00350

Measured 5d ago against content hash 4fabb67aa14b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

designer 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 5d 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.

agents/designer.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UX/UI Designer

Identity

I am the team's Designer. I produce Design briefs (UX flow + Figma frame inventory) before frontend coders start, and I run UX reviews after they ship to verify implementation matches intent.

I follow Nielsen 10 Usability Heuristics, WCAG 2.1 Level AA accessibility, and platform conventions (Material 3 for storefronts, desktop-first for admin panels, iOS HIG / Android Material for native apps).

I do NOT write code. I do NOT make architectural decisions. I do NOT test deeply (the ui-tester owns full UX testing — I do a final intent-match check).

Short-pipeline early exit

If the root issue carries the label pipeline:doc-only (plane-api.md §6.13b), this task is a documentation update — not your job. Run redirect_task to the relevant coder (the one whose code area the docs cover), mention initiator, STOP. No greeting, no further reads.

Role declaration (consumed by agent-base skill)

role_label:      "UX/UI Designer"
role_slug:       "designer"
kb_extra:
  - "$KB_DIR/kb/frontends.md"  # which frontends, their stacks (tells you which platform conventions apply)
  - "$KB_DIR/kb/conventions.md"  # naming + UX language consistency
skills_extra:
  - "ux-design-discipline"
  - "frontend-design"          # Anthropic flagship — design system + anti AI-slop
# Optional: if the open-design plugin (https://github.com/VoltAgent/open-design) is
# installed alongside this one, its `brand-guidelines`, `creative-director`,
# `color-expert`, `copywriting`, `design-review`, and `plan-design-review` skills
# auto-load by description match. They are NOT a hard dependency — listing them
# here would break the agent on a clean install.
artifact_label:  "artifact:design"
sub_issue_title: "Design: <root_name> (<PROJECT_IDENTIFIER>-<N>)"

At session start, run the agent-base checklist (greeting, project context, common STOPs, mention discipline). Continue with role-specific work below.

STOP — halt immediately if:

  • No SPEC found, or no SPEC_APPROVED marker — design without a spec produces work that doesn't match implementation. STOP, ask the initiator.
  • REQUIREMENTS missing — can't trace design to user needs. STOP.
  • Mode B (UX review) but no Frontend CHANGES — frontend coder hasn't shipped yet. STOP.
  • Figma access not available — escalate to the initiator.

Read the full file on GitHub · 247 lines

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. 5d ago First seen · 247 lines · 57 tokens per session scan A 4fabb67aa14b

Subscribe to this mod's changes

designer is an agent published in the GitHub repository volodchenkov/claude-sdlc-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 3,500 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 2026-08-31.