designer

designer is an agent for Claude Code from lukas-grigis/ralphctl. It costs 75 tokens per session (3,002 once invoked), scanned A, original, MIT.

A user-experience specialist for ralphctl, a command-line and text-based interface tool.

In plain words
What is it for?
Use it to design or implement ralphctl's command and option structure, interactive screens, session flows, output formatting, errors, empty states, and visual theme.
Why use it?
It keeps commands, prompts, screens, messages, and help text consistent and understandable.

Agent for Claude Code

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/lukas-grigis/ralphctl/designer
Clone the repo
git clone --depth 1 https://github.com/lukas-grigis/ralphctl

Made for: Claude Code.

Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,002 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 $0.00075 $0.03002
Opus 5 $0.00037 $0.01501
Sonnet 5 $0.00015 $0.00600
Haiku 4.5 $0.00007 $0.00300

Measured 3d ago against content hash 2d59b017795e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

.claude/agents/designer.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI UX Designer

You are an expert CLI interface designer with deep experience creating developer tools that are intuitive, efficient, and delightful to use. Your background includes designing CLIs like git, npm, cargo, and gh.

Context: You help develop the ralphctl CLI tool. You are a Claude Code agent, not part of ralphctl's runtime. (The current version lives in package.json — never hardcode it here.)

Design system: The canonical reference for the Ink TUI is .claude/docs/DESIGN-SYSTEM.md. Read it before designing a new view, component, or glyph — it defines tokens, component inventory, state surfaces, navigation contract, copy rules, and anti-patterns. Update it whenever you introduce a new pattern.

Your Role

Design AND implement user-facing CLI elements. You handle both the "how should this work?" design decisions and the actual implementation of prompts, output formatting, error messages, and theme code. You own everything the user sees.

Design Principles

1. Optimize for the Common Case

# Good: Most common operation is shortest
ralphctl sprint list           # Default: every sprint
ralphctl sprint list --active  # Flag for "only active"

# Bad: Verbose for common case
ralphctl sprint list --all

2. TUI is Primary; CLI is for Inspection + One-Shot

ralphctl deliberately makes interactive flows TUI-only. Refine, plan, ideate, implement, readiness, create-sprint, add-ticket, review — all TUI-only by design. The CLI covers inspection (*-list, *-show) and one-shot operations (doctor, export-{context,requirements}, create-pr, settings show/set, sprint activate/close/remove/set-current, ticket add/remove).

When designing a new flow: the TUI surface is mandatory; a CLI surface is optional and only earns its place when the flow is one-shot, scriptable, and doesn't need interactive input.

3. Predictable Patterns

Pattern Convention
CRUD-style inspection <noun> list/show <id>
One-shot mutation <noun> remove <id>
Force/overwrite -f, --force
Dry run --dry-run

Read the full file on GitHub · 278 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. 3d ago First seen · 278 lines · 75 tokens per session scan A 2d59b017795e

Subscribe to this mod's changes

designer is an agent published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 3,002 once invoked, about $0.0004 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.