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.
npx skills add marcoguillermaz/Tierward --skill responsive-auditgit clone --depth 1 https://github.com/marcoguillermaz/TierwardWrote 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/skills/marcoguillermaz/tierward/responsive-audit)<a href="https://agentmods.dev/skills/marcoguillermaz/tierward/responsive-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/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/skills/marcoguillermaz/tierward/responsive-audit"><img src="https://agentmods.dev/badge/skills/marcoguillermaz/tierward/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 | $0.00000 | $0.04974 |
| Opus 5 | $0.00000 | $0.02487 |
| Sonnet 5 | $0.00000 | $0.00995 |
| Haiku 4.5 | $0.00000 | $0.00497 |
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 9d 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 — 367 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration (fill in before first run)
Replace these placeholders:
[DEV_URL]- e.g.http://localhost:3000[LOGIN_ROUTE]- your login page path, e.g.login,signin,auth/login[SITEMAP_OR_ROUTE_LIST]- e.g.docs/sitemap.mdordocs/routes.md[MOBILE_ROUTES]- comma-separated routes to test in quick mode (pick 4–6 most-used)[TEST_ACCOUNTS]- one or moreemail / passwordpairs per role (from your project's test accounts)[DEV_COMMAND]- e.g.npm run dev,pnpm dev[APP_SOURCE_GLOB]- e.g.src/**/*.{tsx,jsx},app/**/*.{vue,svelte},templates/**/*.html[SCOPE_NOTE]- which roles/pages are in scope vs excludedIf
[DEV_URL]or[SITEMAP_OR_ROUTE_LIST]is not filled, the skill reports an error and exits.
Step 0 - Mode + target detection
Parse $ARGUMENTS:
Mode (controls breakpoints, route breadth, and WCAG checks):
quick(or empty) → BP1 (375px) only, key routes per role. No WCAG checks.full→ all breakpoints (375px + 768px + 1024px), all R-flagged routes. No WCAG checks.wcag→ adds BP0 (320px) to the active breakpoint set + WCAG 1.4.4 resize text step (Step 5b). Stackable:full wcag= all breakpoints + WCAG compliance checks.
Target (filters the route list - applied on top of mode):
target:role:<role_name>→ routes accessible by that role onlytarget:section:<name>→ routes whose path contains<name>- No target → NO filter - ALL R-flagged routes from
[SITEMAP_OR_ROUTE_LIST]per the selected mode
STRICT PARSING - mandatory: derive mode and target ONLY from the explicit text in $ARGUMENTS. Do NOT infer target from conversation context, recent work, active block names, or project memory. If $ARGUMENTS contains no target: token → apply NO filter (all R-flagged routes per the selected mode).
Target scoping - comparative vs independent checks (mandatory): some audit skills contain comparative checks that derive a project-wide convention by counting usage across the whole inventory - those must ignore the target: filter. This skill has none: every check tests a route, breakpoint, or file against an absolute threshold (WCAG 1.4.10 reflow at 320px, 44px tap targets, 8px spacing, WCAG 1.4.4 at 200%).
- Comparative checks - full-project by design; the
target:filter does NOT apply to them: none. No check derives its baseline by counting across the route inventory. - Independent checks - target-safe: all checks (S1-S3 static pre-checks, R1-R9 breakpoint checks, VR1-VR6 visual checks, Step 5b WCAG 1.4.4) evaluate one route/file in isolation and safely honor the
target:filter. - When a
target:is given: apply the filter to the working route list (Step 1) and to the static pre-check file scope; no check runs outside the target scope, and the report states the audited scope explicitly.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 367 lines · 0 tokens per session scan A e6724b046c12
responsive-audit is a skill published in the GitHub repository marcoguillermaz/Tierward (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,974 tokens. 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.
Other skills, from other repositories
visual-qa-vision-agent
Equips the AI agent with visual QA capabilities using Playwright/Puppeteer and the agent's innate Vision capabilities to self-correct UI layout, CSS alignment, and visual regressions.
image-compare
Compare two image files on disk and report what changed, region by region. Trigger on "what changed between these two images", "diff these PNGs", "did this render drift", "compare screenshots/exports/renders".
e2e
Generate and run Playwright E2E tests traced to spec.md acceptance criteria, with an optional accessibility audit. Use when saying "e2e tests" or "a11y audit".
visual-qa-testing
Visually QA a web application by launching it in Cursor's built-in browser, taking screenshots, checking console errors, and auditing network requests. Use after making UI changes to verify they look correct.
ui-aqa-flow
Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.
review-screenshot
A standard workflow for taking screenshots to check a user interface, using a dedicated review process for different verification modes.