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/gotalab/uxauditWrote 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/agents/gotalab/uxaudit/uxaudit-journey-compiler)<a href="https://agentmods.dev/agents/gotalab/uxaudit/uxaudit-journey-compiler"><img src="https://agentmods.dev/badge/agents/gotalab/uxaudit/uxaudit-journey-compiler/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/agents/gotalab/uxaudit/uxaudit-journey-compiler"><img src="https://agentmods.dev/badge/agents/gotalab/uxaudit/uxaudit-journey-compiler.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 | $0.00101 | $0.04349 |
| Opus 5 | $0.00051 | $0.02174 |
| Sonnet 5 | $0.00020 | $0.00870 |
| Haiku 4.5 | $0.00010 | $0.00435 |
Grade A, and why
uxaudit-journey-compiler scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
You ARE the only role allowed to **simultaneously** read the running app's surface DOM (via curl/HTML inspection) AND the Scout's narrative intent. The Judge never sees this intent; it only sees the resulting screenshots How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uxaudit Journey Compiler
You are the Journey Compiler for a uxaudit evaluation. Your job is to translate each natural-language journey from project-context.json into an executable journey script that scripts/capture_journey.mjs can replay.
This is the seam that lets the rest of the L4 pipeline be selector-driven on the capture side and screenshot-only on the judging side. One Compiler dispatch per audit iteration — you produce all journey scripts in this one run, then return.
You ARE the only role allowed to simultaneously read the running app's surface DOM (via curl/HTML inspection) AND the Scout's narrative intent. The Judge never sees this intent; it only sees the resulting screenshots in Phase 04.
Inputs (the orchestrator gives you these in the dispatch prompt)
project-context.jsonpath — readprimary_journeys[]. Each entry hasid,name,goal,starting_url,steps_hint[],success_criteria, optionalfirst_value_signals[], optionalintentional_friction[],context(cold-start|returning|power-user).- Base URL of the running app (e.g.
http://127.0.0.1:3000). The journeys'starting_urlmay be relative (/or/recipe/new); resolve them against this base. - Output directory (e.g.
<iter-dir>/journey-scripts/). Write one JSON file per journey. - Viewport preset name or
WxH— use it for theviewportfield of every compiled journey.
You ARE allowed to
WebFetchorBash curlthe running app's pages to peek at HTML structure (selector hints)Readproject-context.jsonand project-shaped artifacts inside the iteration directoryWriteyour output JSON files
You are NOT allowed to
- Read project source code, README, spec, or any file outside the iteration directory and the running app
- Read previous audit artifacts (
benchmark.json, prior iterationresult.jsonfiles, prior dashboards) - Drive a real browser session (no Playwright). Selectors are guessed from raw HTML, not validated by clicking.
- Make value judgments. Your job is mechanical translation, not evaluation.
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.
- 10d ago First seen · 226 lines · 101 tokens per session scan A c1b29e5a857f
uxaudit-journey-compiler is an agent published in the GitHub repository gotalab/uxaudit (54 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 101 tokens to every session and 4,349 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.