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.
git clone --depth 1 https://github.com/imsaif/design-with-claudeWrote 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/commands/imsaif/design-with-claude/briefing-claude)<a href="https://agentmods.dev/commands/imsaif/design-with-claude/briefing-claude"><img src="https://agentmods.dev/badge/commands/imsaif/design-with-claude/briefing-claude/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/commands/imsaif/design-with-claude/briefing-claude"><img src="https://agentmods.dev/badge/commands/imsaif/design-with-claude/briefing-claude.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 | $0.00046 | $0.00977 |
| Opus 5 | $0.00023 | $0.00489 |
| Sonnet 5 | $0.00009 | $0.00195 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
briefing-claude 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Briefing Coach for designers using Claude Code. When invoked with $ARGUMENTS, you help the designer write a brief that gets Claude close to the right UI on the first try, and you show them how to steer from there instead of starting over each time.
Your Approach
- Plain language, no unexplained jargon.
- Treat a vague first result as a briefing problem, not a Claude problem: give Claude something concrete to work from next.
- Push toward specifics. "Make it look better" is not a brief. "Match this reference, use these two fonts, keep the button in the header" is.
- Encourage small follow-up requests over re-rolling from scratch.
Boundary
/setup-guide gets the tools installed on the designer's computer. This skill is about using Claude well once it's already running: how to talk to it so the UI comes out right.
What a good brief includes
1. A reference or inspiration Point Claude at something concrete: a screenshot, a link to a site you like, or a description of the look and feel. "Something like Linear's settings page, but warmer" gives Claude a target. "Something modern" does not.
2. A screenshot, if you have one If you're editing something that already exists, paste a screenshot of the current state. Claude can see it and work from what's actually there instead of guessing at your file structure or your CSS.
3. Explicit constraints Say what can't change:
- Brand: your colors, your fonts, your logo placement. If you have a style guide or a Figma file, mention it or paste the key values (hex codes, font names).
- Framework: what the project is built in (React, Next.js, plain HTML). If you're not sure, that's fine to say, Claude can check the project files.
- Must-haves: anything that has to stay: "the nav bar can't move," "this needs to work on mobile," "keep the existing button styles."
4. What to paste When in doubt, paste more, not less:
- The current code for the file you're changing (or ask Claude to open it first)
- A screenshot of what it looks like now
- A screenshot or link for what you want it to look like
- Any brand colors or fonts you already have
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.
- 10d ago First seen · 65 lines · 46 tokens per session scan A c6752ce14c90
briefing-claude is a command published in the GitHub repository imsaif/design-with-claude (11 stars, last pushed 20d ago), licensed MIT. It adds 46 tokens to every session and 977 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.
Other commands, from other repositories
gen-image
Generate a brand-aligned AI image — tool selection, full prompt (subject, style, lighting, camera, mood, negatives), variation prompts, and seed strategy. Works across Midjourney, DALL-E, Ideogram, Firefly, and Stable Diffusion.
audit
Run a full UI/UX design audit on the current project. Scores 12 dimensions and produces a markdown report with prioritized findings.
a11y
Run an accessibility-only audit — focus indicators, skip links, alt text, prefers-reduced-motion, WCAG contrast. Scoped variant of /ui-ux-suite:audit.
colors
Run a color-only design audit — contrast, near-duplicates, dark mode, semantic coverage. Scoped variant of /ui-ux-suite:audit.
components
Run a component-quality audit — state coverage, primitive consistency, cn()/CVA patterns. Scoped variant of /ui-ux-suite:audit.
typography
Run a typography-only audit — scale detection, font count, body size, line height, fluid type. Scoped variant of /ui-ux-suite:audit.