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-security-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-security-scan)<a href="https://agentmods.dev/skills/mauricioperera/kdd/kdd-security-scan"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-security-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-security-scan"><img src="https://agentmods.dev/badge/skills/mauricioperera/kdd/kdd-security-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 | $0.00140 | $0.02034 |
| Opus 5.5 | $0.00056 | $0.00814 |
| Sonnet 5.5 | $0.00028 | $0.00407 |
| Haiku 4.5 | $0.00014 | $0.00203 |
Grade A, and why
kdd-security-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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Scan (Capa 3 de KDD)
Produce hallazgos de seguridad de un repositorio en el formato de contrato que audita la Capa 3 de KDD. Esta skill NO es el gate -- es la parte creativa/no determinista (la hace un LLM, con o sin subagentes) que el gate despues valida. Distincion central: el agente decide QUE es un hallazgo; el gate solo audita que el artefacto sellado cumpla forma y politica. Ningun LLM participa en el gate.
Adaptada del flujo de las skills de
openai/codex-security
(_bundled_plugin/skills/security-scan/, Apache-2.0), quitando toda dependencia del
binario codex y de sus tools MCP especificas de la app de escritorio. Esta version
corre con Bash + lectura de archivos nada mas -- cualquier agente sirve.
Cuando usarla
El usuario pide auditar un repo (propio o externo) por vulnerabilidades 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
repo_root: raiz del repositorio a escanear (puede ser un clon separado del propio KDD -- ver la nota de portabilidad enscripts/vendor/codex-security/README.md, el finalizer no asume que el target viva dentro del repo KDD).scan_dir: donde vas a escribir los 3 JSON. Por defectosecurity/scandentro del repo KDD (coincide con el default devalidate_security_findings.py); si estas gobernando un repo EXTERNO, cualquier directorio disponible sirve, con tal de que se lo pases explicito afinalize_scan_contract.py --scan-dir.- Los 3 schemas viven en
knowledge/data_models/security/(vendorizados del mismo origen, no los reinventes ni los edites).
Flujo
1. Alcance
Antes de tocar codigo, fija por escrito (2-3 lineas, no hace falta un documento
aparte): que directorio/paquete se revisa, que queda explicitamente fuera, y contra
que amenaza (codigo de terceros ejecutado localmente, superficie de red expuesta,
manejo de secretos, etc.). Esto se vuelca en scan.scope.summary del manifest.
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 · 142 lines · 140 tokens per session scan A 4e749d3826a0
kdd-security-scan is a skill published in the GitHub repository MauricioPerera/KDD (11 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 2,034 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.
firecrawl-build-search
Integrate Firecrawl /search into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.
firecrawl-build-scrape
Integrate Firecrawl /scrape into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.
firecrawl-build-interact
Integrate Firecrawl /interact into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain /scrape cannot complete.