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/gonzalezpazmonica/saviaWrote 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/gonzalezpazmonica/savia/accessibility-mode)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/accessibility-mode"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/accessibility-mode/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/gonzalezpazmonica/savia/accessibility-mode"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/accessibility-mode.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 | $0.00019 | $0.00546 |
| Opus 5 | $0.00010 | $0.00273 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
accessibility-mode 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- accessibility-mode — 100% identical, 0 lines differ
What it actually says
/accessibility-mode [acción]
Toggle rápido para gestionar la accesibilidad sin pasar por el wizard completo.
Parámetros
on— Activa la accesibilidad con los últimos ajustes guardadosoff— Desactiva temporalmente (los ajustes se conservan para reactivar)status— Muestra qué adaptaciones están activas y qué hacenconfigure— Permite cambiar un ajuste específico sin repetir todo el setup- Sin parámetro → equivale a
status
Flujo
Status
Lee .claude/profiles/users/{slug}/accessibility.md y muestra:
🦉 Accesibilidad — Estado actual
Visión:
Lector de pantalla: ✅ activado → sin ASCII art, output estructurado
Alto contraste: ❌ desactivado
Motor:
Acomodación motora: ❌ desactivado
Cognitivo:
Carga cognitiva: baja → mensajes cortos, paso a paso
Trabajo guiado: ✅ nivel alto → Savia pregunta antes de cada paso
Sensibilidad en reviews: ✅ → lenguaje constructivo
Bienestar:
Pausas: Pomodoro cada 25 min
Para cambiar: /accessibility-mode configure
Para desactivar todo: /accessibility-mode off
Configure
Pregunta qué ajuste cambiar:
"¿Qué quieres cambiar? Puedes decirme cosas como 'activa lector de pantalla', 'cambia pausas a 52-17', 'sube la carga cognitiva a media'."
Actualiza solo el campo indicado y confirma.
On / Off
on→ pone todos los campos a sus últimos valores guardadosoff→ temporalmente desactiva (añade campotemporarily_disabled: true)
Output Template
resultado:
accion: "status|on|off|configure"
ajustes_activos: [lista]
Restricciones
- Si no existe
accessibility.mdy el usuario ejecutastatus→ sugerir/accessibility-setup - Nunca eliminar el fichero con
off, solo marcar como temporalmente desactivado - En
configure, aceptar lenguaje natural ("quiero que me hables más corto" → cognitive_load: low)
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.
- 3d ago First seen · 76 lines · 19 tokens per session scan A 84241d8610d8
accessibility-mode is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 546 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 2026-09-06.
Other commands, from other repositories
deja
Search this machine's past AI coding sessions (deja-vu).
seo-report
Generates a complete SEO report in markdown — combines technical audit, content and schema in one document with an overall score and prioritized action plan. TRIGGER when the user enters /seo-report or asks for a full SEO report, SEO summary or SEO audit report.
seo-speed
Analyzes the site load performance — bundle size, unoptimized images, render-blocking scripts, missing lazy loading and estimated Core Web Vitals. TRIGGER when the user enters /seo-speed or asks to analyze speed, performance or Core Web Vitals.
seo-content
Analyzes content quality — length, readability, thin content, internal duplicate content and topic expansion opportunities. TRIGGER when the user enters /seo-content or asks to analyze content quality, thin content, readability or topic coverage.
seo-meta
Reviews and generates optimized meta titles and descriptions for all pages. Checks length, keywords, uniqueness and potential CTR. TRIGGER when the user enters /seo-meta or asks to review, improve or generate meta tags, title tags or meta descriptions.
seo-schema
Audits the site's structured data (JSON-LD) — verifies schema types, required fields, validation errors and rich snippet opportunities. TRIGGER when the user enters /seo-schema or asks to review or generate structured data, JSON-LD, schema markup or rich snippets.