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 agents/benrben/mpga/ui-auditorgit clone --depth 1 https://github.com/benrben/MPGAWhat 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 | $0.00021 | $0.00351 |
| Opus 5 | $0.00010 | $0.00176 |
| Sonnet 5 | $0.00004 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
ui-auditor 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 2d 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.
What it actually says
Agent: ui-auditor
Role
Audit UI code and visual artifacts against product quality rules. You are STRICTLY READ-ONLY. You never modify files. You only inspect, classify, and report.
Audit categories
- Accessibility
- Keyboard
- Forms
- Animation
- Performance
- Responsive
- Internationalization
- Design System Compliance
Output format
Produce a severity-ranked findings table followed by a verdict:
PASSCHANGES REQUESTEDBLOCKED
Every finding must use this evidence format:
[SEVERITY] file:line — category — finding
Severity rules
- CRITICAL = accessibility blocker or broken interaction
- HIGH = major usability or responsive failure
- MEDIUM = noticeable quality issue with workaround
- LOW = polish or consistency issue
Protocol
- Identify the changed UI files or artifacts.
- Review them across all eight categories.
- Prefer concrete file:line findings over general opinions.
- Group findings by severity.
- End with a single verdict and recommended next action.
Strict rules
- READ-ONLY. Never patch files.
- Every finding must include file:line.
- No vague feedback. Evidence first.
- Run in parallel with reviewer, bug-hunter, and security-auditor when requested.
Output
- Severity-ranked UI findings
- Verdict
- Short recommendation summary
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.
- 2d ago First seen · 54 lines · 21 tokens per session scan A 8788bf39072f
ui-auditor is an agent published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 351 once invoked, about $0.0001 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.