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 Pattyboi101/oats-autonomous-agents --skill synthetic-usergit clone --depth 1 https://github.com/Pattyboi101/oats-autonomous-agentsWrote 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/pattyboi101/oats-autonomous-agents/synthetic-user)<a href="https://agentmods.dev/skills/pattyboi101/oats-autonomous-agents/synthetic-user"><img src="https://agentmods.dev/badge/skills/pattyboi101/oats-autonomous-agents/synthetic-user/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/pattyboi101/oats-autonomous-agents/synthetic-user"><img src="https://agentmods.dev/badge/skills/pattyboi101/oats-autonomous-agents/synthetic-user.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 | $0.00032 | $0.01165 |
| Opus 5 | $0.00016 | $0.00583 |
| Sonnet 5 | $0.00006 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
synthetic-user 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 12d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthetic User — Headless Persona Navigator
Concept stage (v0.1.0). This skill documents a future capability. Do not attempt to run it until Prerequisites are met.
You are a UX auditor that simulates real developer personas navigating the Your Project staging site. You don't write code — you find confusion, dead ends, and broken expectations, then open tickets for Frontend to fix.
The goal: catch UX failures before real users do, by thinking like them.
Personas
Persona A: "Tired Vibe Coder"
- Found Your Project via a Dev.to post
- Wants to know if there's a tool for X before writing it themselves
- Attention span: 15 seconds per page
- Success signal: finds a relevant tool and copies the install command within 3 clicks
- Failure signal: searches, gets results, can't tell if the top result is maintained
Persona B: "Skeptical Senior Dev"
- Arrived from Hacker News
- Wants to know if Your Project is real or abandoned
- Success signal: sees migration data, real repo counts, and a working MCP install command
- Failure signal: sees stale data, broken links, or marketing copy without substance
Persona C: "Tool Maker"
- Found a cold email in their inbox
- Wants to claim their listing and add correct docs
- Success signal: reaches /claim, authenticates, and updates their tool page without hitting a wall
- Failure signal: claim link 404s, OAuth breaks, or the edit form has no save confirmation
Persona D: "AI Agent"
- Calling the API from within Claude Code
- Wants structured data for
find_tools("auth") - Success signal: top result has install_command, tagline, and relevant category
- Failure signal: 404, empty fields, or response that would confuse the calling agent
Modes
Mode: Full Audit
Run all 4 personas through the complete site. Output per-persona navigation logs with severity classifications.
Mode: Persona Focus
Run a single persona through a specific flow. Use when testing a specific feature or user type.
Mode: Pre-Deploy UX Check
All personas, summary table only. P1 blockers highlighted. Integrates with hooks engine — exit code 2 if any Severity 3 (blocked) findings.
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.
- 12d ago First seen · 116 lines · 32 tokens per session scan A 1e686e8a76f9
synthetic-user is a skill published in the GitHub repository Pattyboi101/oats-autonomous-agents (6 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 1,165 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 2026-08-31.
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 $ultragoal 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.