bolder

bolder is a command for Claude Code from Muminur/frontend-design-craft-skill. It costs 12 tokens per session (385 once invoked), scanned A, original, MIT.

A design-review command that pushes a visually safe or generic interface toward a more distinctive look. It can focus on typography, colour, layout, or visual density.

In plain words
What is it for?
Use it to make a website or interface more visually daring by changing its headline scale, colour choices, page structure, spacing, or type styles.
Why use it?
It helps when a technically correct design feels bland, overly corporate, or too similar to common software sites.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the craft plugin — 4 skills, 13 commands shipped together

Good fit Use it to make a website or interface more visually daring by…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/muminur/frontend-design-craft-skill/bolder
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.

Clone the repo
git clone --depth 1 https://github.com/Muminur/frontend-design-craft-skill

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 4 skills, 13 commands.

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 bolder

README.md
[![agentmods](https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/bolder.svg)](https://agentmods.dev/commands/muminur/frontend-design-craft-skill/bolder)
Your own site
<a href="https://agentmods.dev/commands/muminur/frontend-design-craft-skill/bolder"><img src="https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/bolder.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 385 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00012 $0.00385
Opus 5 $0.00006 $0.00192
Sonnet 5 $0.00002 $0.00077
Haiku 4.5 $0.00001 $0.00038

Measured 6d ago against content hash 193909873017, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

bolder 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 6d 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.

commands/bolder.md · 41 lines

What it actually says

/bolder

The design is technically correct but boring. It looks like every other SaaS site. Push it.

Target

$ARGUMENTS

Procedure

  1. Diagnose the boring. What specifically makes it generic? Likely candidates:
    • Centered hero with predictable structure
    • Safe blue or corporate-purple color
    • Conservative type sizes (everything between 16px and 36px)
    • Symmetric grids only
    • No personality in copy
  2. Pick one bold lever first. Do not push everything at once.
    • Typography lever: Increase display sizes dramatically (96px+ headlines), introduce a serif for emotional moments, or commit to a single distinctive face.
    • Color lever: Replace safe blue with a confident non-default — deep green, terracotta, oxblood, electric blue at lower saturation, sand.
    • Layout lever: Break the centered hero. Use a 7/5 asymmetric split. Put the headline at an unexpected scale or position.
    • Density lever: Either way more whitespace, or way more density — both feel intentional.
  3. Commit. Half-bold reads as confused. If you raise the headline to 96px, also raise its weight, also tighten the tracking, also reduce surrounding noise.
  4. Re-check restraint elsewhere. When one element gets bold, others must get quieter. A bold headline next to a busy background is just chaos.

Output

## Bolder

**Lever pulled:** [typography | color | layout | density]
**Specific changes:**
  - [list]
**Restraint applied to balance:**
  - [list of things that were toned down]
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. 6d ago First seen · 41 lines · 12 tokens per session scan A 193909873017

Subscribe to this mod's changes

bolder is a command published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 12 tokens to every session and 385 once invoked, about $0.0001 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.