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/JubaKitiashvili/everything-react-native-expoWrote 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/commands/jubakitiashvili/everything-react-native-expo/erne-debug-visual)<a href="https://agentmods.dev/commands/jubakitiashvili/everything-react-native-expo/erne-debug-visual"><img src="https://agentmods.dev/badge/commands/jubakitiashvili/everything-react-native-expo/erne-debug-visual/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/commands/jubakitiashvili/everything-react-native-expo/erne-debug-visual"><img src="https://agentmods.dev/badge/commands/jubakitiashvili/everything-react-native-expo/erne-debug-visual.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 | $0.00018 | $0.00594 |
| Opus 5.5 | $0.00007 | $0.00238 |
| Sonnet 5.5 | $0.00004 | $0.00119 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
erne-debug-visual 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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/erne-debug-visual — Visual Debugging
You are executing the /erne-debug-visual command. Use the visual-debugger agent for screenshot-based UI analysis and fixing.
Arguments
/debug-visual — auto-capture screenshot from running simulator/emulator via agent-device
/debug-visual <file> — analyze a specific screenshot file
/debug-visual --compare <figma-file> — compare app screenshot with Figma export
/debug-visual --screen <ScreenName> — navigate to and capture a specific screen
Process
Step 1: Capture Screenshot
- No args: auto-capture from running simulator/emulator via agent-device
<file>provided: read the specified screenshot file directly--compare: capture live app screenshot AND read the Figma export file--screen: navigate to the named screen first, then capture
Step 2: Analyze
- Apply multimodal vision to the screenshot(s)
- Read the relevant component source files
- Identify all visual issues
- Present a numbered list — each item includes category and severity:
| Category | Examples |
|---|---|
| Layout | overflow, misalignment, wrong spacing |
| Typography | wrong font, size, weight, truncation |
| Color | wrong token, contrast failure, dark mode |
| Spacing | padding/margin off-spec |
| Responsive | breaks on small/large screen |
| Figma Delta | deviation from design (--compare only) |
Severity: critical · major · minor
Step 3: Interactive Fix
- User picks issue numbers to fix
- Locate the responsible component in source
- Apply the fix (minimal change, match project style)
- Hot reload — allow ~2s for changes to reflect
- Re-capture screenshot
- Show before/after comparison
- Ask: "Does this look correct? Any remaining issues?"
Step 4: Summary
- Issues detected (count by severity)
- Fixes applied with before/after diff per issue
- Remaining issues (if any deferred by user)
- Save findings to memory for future reference
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.
- 8d ago First seen · 79 lines · 18 tokens per session scan A 4c11c46ff007
erne-debug-visual is a command published in the GitHub repository JubaKitiashvili/everything-react-native-expo (49 stars, last pushed 8d ago), licensed MIT. It adds 18 tokens to every session and 594 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-09.
Other commands, from other repositories
ux-audit
Walk a live web app AS a real user — interaction-first methodology. Hard gates (console / network / layout-collapse), Persona Lock, Interaction Manifest enforcement, multi-pane stress, visual polish, perfection checklist, 11 scenarios (judgement-density-ordered), Top 5 + self-critique pass + smallest-possible-patch +…
error-flow
Design an error flow end to end — prevention, detection, messaging, and recovery paths.
ux-fix
Opt-in fix loop. Reads the latest report from .ux/, validates working tree, and applies findings as atomic commits via the right sub-agents. Triggers on "fix the findings", "apply the fixes", or "run the fix loop". Use when applying findings from a previous audit / copy / a11y / motion / polish report, the user says…
ux-lint
Lint docs/ux for integrity and drift — missing Figma frames, unresolved SCR/story traces, orphans, built screens without coverage, index desync, broken links.
error-handling-specialist
Use when things go wrong badly. Error messages that blame the user, validation firing at the wrong moment, form data lost on failure, dead-end 404 and 500 pages, or no way to retry.
audit
Read and follow the instructions in agents/skills/audit.md. Also read and follow agents/frontend-design/design-all.md and any referenced files in agents/frontend-design/reference/ as needed.