Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MauricioPerera/KDDnpx agentmods add skills/mauricioperera/kdd/kdd-accessibility-scanWrote 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/skills/mauricioperera/kdd/kdd-accessibility-scan)<a href="https://agentmods.dev/skills/mauricioperera/kdd/kdd-accessibility-scan"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-accessibility-scan/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/skills/mauricioperera/kdd/kdd-accessibility-scan"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-accessibility-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00146 | $0.01991 |
| Opus 5.5 | $0.00058 | $0.00796 |
| Sonnet 5.5 | $0.00029 | $0.00398 |
| Haiku 4.5 | $0.00015 | $0.00199 |
Grade A, and why
kdd-accessibility-scan 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 2mo 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accessibility Scan (Capa 3 de KDD -- WCAG)
Produce hallazgos de auditoria de accesibilidad en el formato de contrato que audita la Capa 3 de KDD. Esta skill NO es el gate -- es la parte creativa/no determinista (correr un scanner automatizado, complementar con revision manual, mapear cada violacion a un criterio WCAG) que el gate despues valida. Distincion central: el scanner/agente decide QUE es un hallazgo de accesibilidad; el gate solo audita que el artefacto sellado cumpla forma y politica de calidad de datos.
Como kdd-compliance-scan y
kdd-privacy-scan, este dominio NO vendoriza
ningun sellador externo -- vos mismo escribis findings.json ya en forma final.
No es lo mismo que validate_ux_page.py
KDD ya tiene un gate mecanico, scripts/validate_ux_page.py (ver
validacion.md): un linter estatico que corre
SIN ejecutar nada, sobre paginas HTML AUTOCONTENIDAS del propio repo
(examples/ux-page/ por defecto) -- contraste sobre pares explicitos, i18n,
prefers-reduced-motion. Esta skill es OTRA cosa: gobierna una auditoria real
(automatizada y/o manual) sobre el PRODUCTO en ejecucion, con cobertura mucho mas
amplia (formularios, navegacion por teclado, lectores de pantalla, SPAs). Los dos
gates coexisten sin conflicto -- ver la seccion correspondiente en
knowledge/data_models/accessibility_findings.md.
Cuando usarla
El usuario pide auditar la accesibilidad de un producto/pagina en ejecucion y quiere el resultado gobernado por KDD (versionable, gateado en CI, con politica declarativa), no un reporte suelto en prosa.
Insumos que necesitas antes de empezar
target: URL o build local del producto a auditar.scan_dir: donde vas a escribirfindings.json. Por defectoaccessibility/scandentro del repo KDD (coincide con el default devalidate_accessibility_findings.py); si estas gobernando un producto EXTERNO, cualquier directorio disponible sirve, con tal de pasarselo explicito al gate.- El schema completo vive en
knowledge/data_models/accessibility/findings.schema.json-- consultalo si dudas de un campo, no adivines la forma.
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.
- 2mo ago First seen · 150 lines · 146 tokens per session scan A e93ce5ba231e
kdd-accessibility-scan is a skill published in the GitHub repository MauricioPerera/KDD (11 stars, last pushed today), licensed MIT. It adds 146 tokens to every session and 1,991 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
crit-cli
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
crit-story
Author a crit story and continue the interactive review loop only when the user explicitly invokes crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
anchor-prior-test
Empirically test whether a candidate term qualifies as a semantic anchor by probing how densely it sits in LLM training data — across several model tiers in a clean room — before proposing it. Use when triaging an anchor proposal, deciding anchor vs contract, or vetting a rename. Produces a verdict against the four…
linked-intent-dev
Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…
bidirectional-differential
Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then classifies the drift between them. Use when the user invokes /differential-audit, asks to audit EARS-to-code drift for a feature…