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 agentmods add instructions/aboudjem/ui-ux-suite/agents-mdgit clone --depth 1 https://github.com/Aboudjem/ui-ux-suiteWrote 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/instructions/aboudjem/ui-ux-suite/agents-md)<a href="https://agentmods.dev/instructions/aboudjem/ui-ux-suite/agents-md"><img src="https://agentmods.dev/badge/instructions/aboudjem/ui-ux-suite/agents-md.svg" alt="Measured on agentmods" 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 | $0.01540 | $0.01540 |
| Opus 5 | $0.00770 | $0.00770 |
| Sonnet 5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
ui-ux-suite AGENTS.md 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 yesterday.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: ui-ux-suite
Guidance for AI coding agents working with or invoking this repo. Companion to README.md (which is for humans). This file follows the AGENTS.md convention: standard Markdown, no required fields.
What this tool is
ui-ux-suite is a zero-dependency design linter. It audits a project's CSS, JSX, HTML, and
Tailwind config and returns findings that are located (file:line + selector),
measured (the real wrong value), and fixed (a concrete before → after), across
12 design dimensions grounded in WCAG 2.2, APCA contrast, and the Laws of UX. It is
audit-then-suggest: every run is read-only and never edits the audited project.
How an AI agent should invoke it
Preferred: the MCP tool uiux_audit_run
The MCP server runs over stdio with zero dependencies. Start it with npx ui-ux-suite --mcp,
then call the uiux_audit_run tool. Arguments:
projectPath(string, defaultcwd): the directory to audit.dimensions(string[], optional): scope to specific dimensions; omit for all 12.depth("quick"|"deep", default"quick"):"deep"needs abaseUrland the optional peer deps; otherwise use"quick"(static, no browser).baseUrl(string, optional): running app URL for deep mode.format("full"|"summary"|"json", default"full").
The result includes scoreCard.overall, scoreCard.grade, scoreCard.dimensions[], and
scoreCard.topFindings[]. Each finding carries
evidence: { file, line, col, selector, measured, threshold }, a fix, before/after,
and a citation (wcag: [] success criteria and/or laws: [] slugs).
When insufficientEvidence is true, overall/grade are null and there are no
findings; report that the project lacked enough evidence rather than inventing a score.
Other useful tools: uiux_scan_project (stack detection), uiux_check_contrast (WCAG +
APCA for a color pair), uiux_extract_colors / uiux_extract_typography /
uiux_extract_spacing (values with file/line/selector), uiux_score_dimension,
uiux_score_overall, uiux_laws_query, uiux_knowledge_query.
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.
- yesterday Changed · +10 lines · +216 tokens per session 83855c211a84
- 5d ago First seen · 109 lines · 1,324 tokens per session scan A bc2a9fc05d41
ui-ux-suite AGENTS.md is an instructions file published in the GitHub repository Aboudjem/ui-ux-suite (7 stars, last pushed yesterday), licensed MIT. It adds 1,540 tokens to every session, about $0.0077 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.
Other instructions, from other repositories
naksha-studio copilot-instructions.md
Instructions for Adityaraj0421/naksha-studio, covering naksha design team — github copilot, activation triggers, the design team, design rules for code generation and css custom properties (always use these patterns).
design-with-claude CLAUDE.md
Instructions for imsaif/design-with-claude, covering design-with-claude, project overview, architecture, key files and command file structure.
shadcn-htmx AGENTS.md
Instructions for productdevbook/shadcn-htmx, covering agent guide, hard rules, what's vendored, and when to read each, repos/htmx/ — htmx v4 source (branch: four-dev) and repos/tailwindcss/ — tailwind css v4 source (branch: main).
liquefy-ui CLAUDE.md
Instructions for liquefy-ui/liquefy-ui, covering repository rules, commits, everything else, language and css and visual work.
core-web copilot-instructions.md
Copilot instructions for db-ux-design-system/core-web: All development instructions, build commands, validation steps, coding rules, and the pull request workflow are maintained in AGENTS.md at the repository root. Read that file first before starting any task.
ultimate.UIUX.design.skills AGENTS.md
Instructions for ca-who-codes/ultimate.UIUX.design.skills, covering agents.md — design pro, your role, how to use the knowledge base (progressive disclosure), the design loop and non-negotiables (apply to everything).