Borrowing it
Nothing to install: this file belongs to g-digital-by-Garrigues/EAD-Factory-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/g-digital-by-Garrigues/EAD-Factory-MCP/main/.claude/commands/create-internal-evidence.mdgit clone --depth 1 https://github.com/g-digital-by-Garrigues/EAD-Factory-MCPWrote 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/g-digital-by-garrigues/ead-factory-mcp/create-internal-evidence)<a href="https://agentmods.dev/commands/g-digital-by-garrigues/ead-factory-mcp/create-internal-evidence"><img src="https://agentmods.dev/badge/commands/g-digital-by-garrigues/ead-factory-mcp/create-internal-evidence/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/g-digital-by-garrigues/ead-factory-mcp/create-internal-evidence"><img src="https://agentmods.dev/badge/commands/g-digital-by-garrigues/ead-factory-mcp/create-internal-evidence.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 | $0.00000 | $0.02003 |
| Opus 5 | $0.00000 | $0.01001 |
| Sonnet 5 | $0.00000 | $0.00401 |
| Haiku 4.5 | $0.00000 | $0.00200 |
Grade A, and why
create-internal-evidence 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 12d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Internal Evidence
Registra un fichero en Evidence Manager con custodia interna, sello TSP (eIDAS) y opcionalmente DLT (blockchain Lacnet).
Dos modos de uso:
- Guiado (por defecto): solo pasas el archivo, te pregunta el resto paso a paso con confirmación final
- Rápido: pasas todos los flags y ejecuta directamente
Uso
/create-internal-evidence <ruta> [--title "Título"] [--by "Nombre"] [--tsp-only|--dlt] [--meta "clave:valor, ..."]
Ejemplos:
# Modo guiado
/create-internal-evidence /Users/fvaldez/docs/contrato.pdf
# Modo rápido
/create-internal-evidence /Users/fvaldez/docs/contrato.pdf --title "Contrato 2024" --by "Fernando Valdez" --dlt --meta "cliente:Garrigues, expediente:EXP-2024-001"
Instrucciones
Los argumentos son: $ARGUMENTS
PASO 0 — Detectar modo y parsear argumentos
Extrae del string de argumentos:
filePath: primer token (antes del primer--)title: valor de--title "..."si existecreatedBy: valor de--by "..."si existedlt:truesi--dltestá presente,falsesi--tsp-only,undefinedsi no se especifica ningunometadata: valor de--meta "..."si existe (formato libreclave:valor, clave:valor)
Modo rápido: si están presentes filePath, title (vía --title) Y createdBy (vía --by) Y timestamp preference (--dlt o --tsp-only) → salta al PASO 3.
Modo guiado: si falta cualquiera de los anteriores → ejecuta el flujo interactivo (PASO 1 y PASO 2).
PASO 1 — Validar archivo
Ejecuta: ls -la "<filePath>"
Si no existe, muestra error y detente:
❌ No se encuentra el archivo: <filePath>
Verifica que la ruta sea absoluta y el fichero exista.
PASO 2 — Recopilación guiada (solo en modo guiado)
Haz las preguntas de una en una, esperando respuesta del usuario antes de pasar a la siguiente.
2a. Título (solo si no se pasó --title):
Obtén el nombre base del fichero sin extensión con: basename "<filePath>" | sed 's/\.[^.]*$//'
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.
- 12d ago First seen · 215 lines · 0 tokens per session scan A 4d46fca24084
create-internal-evidence is a command published in the GitHub repository g-digital-by-Garrigues/EAD-Factory-MCP (0 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,003 tokens. 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 commands, from other repositories
sox-compliance
Plan or execute SOX 404 control testing, select audit samples, build testing workpapers, or classify control deficiencies.
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.
review-policy
Review a policy document for structure, coverage, and language quality.
audit-strict
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives.