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 commands/doncheli/don-cheli-sdd/visual-testgit clone --depth 1 https://github.com/doncheli/don-cheli-sddWrote 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/doncheli/don-cheli-sdd/visual-test)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/visual-test"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/visual-test.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.01448 |
| Opus 5 | $0.00041 | $0.00724 |
| Sonnet 5 | $0.00016 | $0.00290 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
visual-test 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 yesterday.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:visual-test
Objetivo
Ejecutar pruebas visuales de componentes UI y páginas completas, comparando capturas de pantalla antes y después de cambios para detectar regresiones visuales. Soporta niveles: página completa, componente individual y breakpoints responsive. Se integra con Computer Use de Claude para testing de interacción.
Uso
/dc:visual-test # Testear todos los componentes registrados
/dc:visual-test --pagina /checkout # Testear una página específica
/dc:visual-test --componente Button # Testear un componente
/dc:visual-test --breakpoints # Testear todos los breakpoints responsive
/dc:visual-test --baseline # Capturar nuevas líneas base
/dc:visual-test --diff-only # Mostrar solo cambios detectados
/dc:visual-test --umbral 2.5 # Tolerancia de diferencia en % (default: 1%)
Comportamiento
-
Cargar configuración desde
.dc/visual-test.yaml- Lista de páginas y componentes a testear
- Breakpoints definidos (mobile, tablet, desktop)
- Umbral de tolerancia de diferencia (default: 1%)
- Directorio de baseline:
.dc/visual-baselines/
-
Modo baseline (
--baseline)- Capturar screenshots actuales como referencia
- Almacenar en
.dc/visual-baselines/<componente>/<breakpoint>.png - Registrar hash de versión y fecha
-
Modo comparación (default)
- Capturar screenshots del estado actual
- Comparar pixel a pixel contra baseline
- Calcular porcentaje de diferencia por componente
- Generar imagen diff con cambios resaltados en rojo
-
Testing de interacción (con Computer Use)
- Simular clicks, hover, focus, scroll
- Capturar estado visual en cada interacción
- Detectar regresiones en estados (hover, active, disabled)
-
Clasificar resultados
- PASS: diferencia ≤ umbral configurado
- WARN: diferencia entre umbral y 5%
- FAIL: diferencia > 5% o componente ausente
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.
- yesterday First seen · 178 lines · 81 tokens per session scan A 245a2a34e85d
visual-test is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 25d ago), licensed Apache-2.0. It adds 81 tokens to every session and 1,448 once invoked, about $0.0004 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 2026-09-03.
Other commands, from other repositories
ui-review
Retroactive visual audit of UI implementation with 1-4 scoring per dimension.
verify-work
Validate built features through conversational UAT.
e2e
Create and run E2E tests across web, mobile, and desktop with auto-detection and CLI-first toolchains.
add-phase
Add phase to end of current milestone in roadmap.
reapply-patches
Reapply local modifications after a PBR update.
remove-phase
Remove a future phase from roadmap and renumber subsequent phases.