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/design-grill)<a href="https://agentmods.dev/commands/imsaif/design-with-claude/design-grill"><img src="https://agentmods.dev/badge/commands/imsaif/design-with-claude/design-grill/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/design-grill"><img src="https://agentmods.dev/badge/commands/imsaif/design-with-claude/design-grill.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 | $0.00038 | $0.01898 |
| Opus 5 | $0.00019 | $0.00949 |
| Sonnet 5 | $0.00008 | $0.00380 |
| Haiku 4.5 | $0.00004 | $0.00190 |
Grade A, and why
design-grill 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior designer running a structured interview. When invoked with $ARGUMENTS, you interrogate a planned or existing design until you and the user share one understanding of it — and you write the shared vocabulary and the binding decisions into the repo while the interview happens, not after.
The problem you exist to solve: context windows end. Design decisions made in conversation evaporate, so session 4 reinvents the button that session 1 agreed on, and a regeneration silently reverts a choice the user deliberately made. What lands in the repo is what survives.
When to skip this
- A one-off visual tweak inside a single session. Just make the change.
- The design is already documented and nothing is being decided. Read the existing files instead.
- The user wants guidance, not interrogation. Use
/design-brief— it answers, this one asks.
Do not run this because it is thorough. Run it when decisions are being made that later sessions must obey.
Step 0: guarantee durability before you ask anything
Artifacts that are not tracked by git do not survive. Check first:
git check-ignore -q .dwic/ && echo IGNORED
If .dwic/ is ignored (dwc's own default), you must resolve it before interviewing. Tell the user plainly and offer the fix:
.dwic/is gitignored, so design decisions written there would not be committed and would not survive this session. I can add negation rules so the decisions are tracked while audit reports stay ignored. Proceed?
On approval, append to .gitignore:
!.dwic/DESIGN-CONTEXT.md
!.dwic/decisions/
If the user declines, write to docs/design-decisions/ instead. Never write design decisions to a path you have confirmed is ignored. If you cannot verify, say so and ask.
The two artifacts
They have different lifetimes, so they live apart.
.dwic/DESIGN-CONTEXT.md — living glossary. Edited freely as meaning sharpens. Design words are genuinely ambiguous and teams think they agree when they do not: "card", "dense", "primary", "muted", "modal" vs "dialog" vs "drawer", "compact". Record what this product means by each term.
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 · 171 lines · 38 tokens per session scan A d0df5eb8212e
design-grill is a command published in the GitHub repository imsaif/design-with-claude (11 stars, last pushed 19d ago), licensed MIT. It adds 38 tokens to every session and 1,898 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
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.
make-creative
Design and produce any fixed-canvas creative — poster, flyer, brochure, business card, social post/ad, story, thumbnail, event banner/signage, infographic, or email — correctly spec'd and on-brand.