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 autousers-ai/mcp --skill autousersgit clone --depth 1 https://github.com/autousers-ai/mcpWrote 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/autousers-ai/mcp/autousers)<a href="https://agentmods.dev/skills/autousers-ai/mcp/autousers"><img src="https://agentmods.dev/badge/skills/autousers-ai/mcp/autousers/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/autousers-ai/mcp/autousers"><img src="https://agentmods.dev/badge/skills/autousers-ai/mcp/autousers.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 | $0.01805 |
| Opus 5 | $0.00000 | $0.00903 |
| Sonnet 5 | $0.00000 | $0.00361 |
| Haiku 4.5 | $0.00000 | $0.00180 |
Grade A, and why
autousers 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autousers
Autousers is a UX evaluation platform: humans and calibrated AI personas (autousers) rate designs against a rubric of dimensions. This Skill teaches you the canonical workflows for driving Autousers through its MCP server.
The MCP server exposes ~40 tools. This Skill is the operating manual for chaining them correctly.
Prerequisite: the MCP must be connected
Every tool referenced in this Skill (evaluations_*, autousers_*, templates_*, teams_*, usage_get, get_usage) is exposed by the @autousers/mcp MCP server. If those tools are not available in your tool list, the user has not connected the MCP yet — point them at the install guide before continuing:
- Server URL:
https://mcp.autousers.ai/mcp - Install docs:
https://autousers.ai/help/mcp - Auth: Bearer
ak_live_*API key minted athttps://app.autousers.ai/settings/api-keys
If evaluations_list returns MissingApiKeyError or 401, the user's API key is missing or revoked — direct them to mint a new one at the URL above.
Open standard: this Skill follows the agentskills.io SKILL.md format, originally introduced by Anthropic in 2025 and now an open spec. The same files work in Claude Code, Claude.ai, the Claude API, and any other agentskills.io-compliant runtime.
Prefer MCP prompts over manual chains
The MCP ships 5 user-invokable prompts (slash commands) that resolve IDs server-side and bake the right tool sequence into a single user turn. Use these first — they save round trips and avoid common mistakes:
| Prompt | When | What it does |
|---|---|---|
/evaluate-url |
"Rate this URL" | Single-sided eval (SSE) on one design |
/compare-designs |
"Compare A vs B" | Side-by-side eval (SxS) on a pair |
/analyze-results |
"Summarise eval X" | Chains results_get → agreement_get → ai_insights_get |
/calibrate-autouser |
"Tune persona Y on eval X" | Kappa loop with optimize/freeze branches |
/triage-low-agreement |
"Why are raters disagreeing?" | Per-dimension kappa breakdown + rubric clarification |
What ships with it
11 files 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.
- reference/auth-and-setup.md 4.6 KB
- reference/domain-glossary.md 6.0 KB
- reference/smart-resolvers.md 3.9 KB
- reference/tool-cheatsheet.md 7.7 KB
- templates/calibration-report.md 2.7 KB
- templates/eval-summary.md 2.9 KB
- workflows/analyzing-results.md 4.3 KB
- workflows/calibration.md 4.9 KB
- workflows/creating-evals.md 5.2 KB
- workflows/managing-templates.md 4.2 KB
- workflows/running-autousers.md 4.7 KB
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 · 85 lines · 0 tokens per session scan A dd5c1319f7ed
autousers is a skill published in the GitHub repository autousers-ai/mcp (0 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,805 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.