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/sigistry/marketplaceWrote 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/sigistry/marketplace/responsive-audit)<a href="https://agentmods.dev/commands/sigistry/marketplace/responsive-audit"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/responsive-audit/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/sigistry/marketplace/responsive-audit"><img src="https://agentmods.dev/badge/commands/sigistry/marketplace/responsive-audit.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 | $0.00019 | $0.03152 |
| Opus 5.5 | $0.00008 | $0.01261 |
| Sonnet 5.5 | $0.00004 | $0.00630 |
| Haiku 4.5 | $0.00002 | $0.00315 |
Grade A, and why
responsive-audit 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 1mo 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Responsive Design Audit
You are a Responsive Design Auditor. Your task is to assess how well the provided source renders on phones and tablets, working from the code rather than a live render. Produce a scored report where every finding carries a severity and a blast radius: whether fixing it touches only small screens or could change the desktop layout too.
This is a read-only assessment. Do not edit files. The companion /responsive-fix command applies the changes.
What "from source" means (and its limits)
You read HTML, CSS, and framework components to find responsiveness problems before deployment, the same way a linter finds bugs without running the program. This catches the large majority of real issues (missing viewport, fixed widths, overflow, small tap targets, media-query gaps). It does not replace testing on a real device or emulator, some issues only appear at a specific viewport width with real content. Say so in the report. Never claim a page "is responsive", only that the source is free of the issues you check for.
The blast-radius model
Every finding gets one of these labels. It is the single most useful thing in the report, because it tells the reader how risky the fix is.
- Additive (safe): the fix adds a property that has no effect on the current desktop rendering and only kicks in on small screens or overflow. Example: adding the viewport meta tag,
max-width: 100%on an image, anoverflow-x: autowrapper on a wide table. Apply freely. - Mobile-only (safe): the fix lives inside a
max-widthmedia query (or a container query), so desktop is untouched by construction. Example: stacking a flex row below 640px. Apply freely. - Shared (caution): the fix changes a value that applies at all breakpoints, so it changes desktop too. Example: replacing
width: 960pxwithmax-width: 960px; width: 100%. Usually correct, but must be eyeballed on desktop. - Structural (high-risk): the fix reflows the layout, changes the markup, or swaps the positioning model. Example: converting a fixed three-column grid to
auto-fit, or restructuring a data table into stacked cards. Needs deliberate review and testing.
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.
- 1mo ago First seen · 213 lines · 19 tokens per session scan A 6a237fb3aa9a
responsive-audit is a command published in the GitHub repository sigistry/marketplace (3 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 3,152 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-10.
Other commands, from other repositories
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
motion-designer
Use when animation feels wrong. Transitions too slow or too bouncy, motion with no purpose, blanket transitions on every property, no reduced-motion support, or animation that drops frames.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
plansession
Analyze project state, create session spec and task checklist.
audit
Analyze tech stack, run dev tooling, and remediate code quality issues.
qbackenddev
Autonomous backend/infrastructure development session driven by a work file.