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 skills add 686f6c61/alfred-dev --skill sbom-generategit clone --depth 1 https://github.com/686f6c61/alfred-devWrote 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/686f6c61/alfred-dev/sbom-generate)<a href="https://agentmods.dev/skills/686f6c61/alfred-dev/sbom-generate"><img src="https://agentmods.dev/badge/skills/686f6c61/alfred-dev/sbom-generate/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/686f6c61/alfred-dev/sbom-generate"><img src="https://agentmods.dev/badge/skills/686f6c61/alfred-dev/sbom-generate.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 | $0.00040 | $0.00743 |
| Opus 5.5 | $0.00016 | $0.00297 |
| Sonnet 5.5 | $0.00008 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
sbom-generate 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generar SBOM (Software Bill of Materials)
Resumen
Este skill genera un inventario completo de todos los componentes de software incluidos en el proyecto, tanto dependencias directas como transitivas. El SBOM es un requisito del Cyber Resilience Act (CRA) europeo y una práctica recomendada de seguridad de la cadena de suministro.
El SBOM permite responder rápidamente a preguntas como "usamos la versión afectada por esta vulnerabilidad?" sin necesidad de investigar manualmente cada proyecto.
Proceso
-
Detectar el ecosistema y las fuentes de dependencias. Identificar todos los ficheros de lock o manifiesto del proyecto:
- Node.js:
package-lock.json,yarn.lock,pnpm-lock.yaml. - Python:
requirements.txt,Pipfile.lock,poetry.lock. - Rust:
Cargo.lock. - Go:
go.sum. - Java:
pom.xml,build.gradle. - PHP:
composer.lock.
- Node.js:
-
Listar dependencias directas. Para cada dependencia directa, registrar:
- Nombre del paquete.
- Versión exacta instalada.
- Licencia.
- Proveedor o autor.
- URL del repositorio.
- Hash de verificación (si está disponible en el lock file).
-
Listar dependencias transitivas. Repetir el mismo proceso para todas las dependencias de las dependencias. Las transitivas suelen ser la mayoría y las más difíciles de rastrear.
-
Incluir componentes no gestionados por paquetes. Algunos componentes se incluyen de forma manual:
- Librerías copiadas directamente (vendoring).
- Scripts de terceros incluidos vía CDN.
- Binarios precompilados.
- Componentes del sistema operativo base (especialmente relevante en contenedores Docker).
-
Generar en formato estándar. Usar uno de los dos formatos aceptados por la industria:
- CycloneDX: formato JSON o XML, preferido por OWASP. Más ligero y centrado en seguridad.
- SPDX: formato estándar ISO (ISO/IEC 5962:2021). Más completo en información de licencias.
Si existen herramientas automáticas para el ecosistema (como
cyclonedx-npm,syft,cdxgen), usarlas. Si no, generar manualmente con la plantillatemplates/sbom.md.
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 · 62 lines · 40 tokens per session scan A 8c062bae4701
sbom-generate is a skill published in the GitHub repository 686f6c61/alfred-dev (105 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 743 once invoked, about $0.0002 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 2026-08-30.
sbom-generate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sbom-generate686f6c61/alfred-dev | Skill | 105 | 2mo ago | MIT | A | 40 | Claude Code |
| plagiarism-checkerbitwize-music-studio/claude-ai-music-skills | Skill | 631 | 2d ago | CC0-1.0 | A | 35 | Claude Code |
| employment-compliancecbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 87 | Claude Code |
| performance-managementcbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 59 | Claude Code |
| revenue-recognitioncbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 69 | Claude Code |
| privacy-and-data-protectioncbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 86 | Claude Code |
| benefits-and-leavecbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 68 | Claude Code |