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/doncheli/don-cheli-sddnpx agentmods add commands/doncheli/don-cheli-sdd/auditar-seguridadWrote 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/doncheli/don-cheli-sdd/auditar-seguridad)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/auditar-seguridad"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/auditar-seguridad/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/doncheli/don-cheli-sdd/auditar-seguridad"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/auditar-seguridad.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 | $0.00020 | $0.01860 |
| Opus 5 | $0.00010 | $0.00930 |
| Sonnet 5 | $0.00004 | $0.00372 |
| Haiku 4.5 | $0.00002 | $0.00186 |
Grade A, and why
auditar-seguridad 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 9d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dc:auditar-seguridad
Objetivo
Realizar una auditoría de seguridad estática del código, identificando vulnerabilidades basadas en OWASP Top 10, exposición de datos sensibles, fallos de autenticación y problemas de configuración.
Uso
/dc:auditar-seguridad # Auditar proyecto completo
/dc:auditar-seguridad @src/services/auth/ # Auditar módulo específico
/dc:auditar-seguridad --foco inyeccion # Enfocarse en un tipo
/dc:auditar-seguridad --severidad critica # Solo hallazgos críticos
Categorías de Auditoría (OWASP Top 10 + extras)
A01: Broken Access Control
Buscar:
❌ Endpoints sin middleware de autenticación
❌ Rutas admin accesibles sin verificar rol
❌ IDOR (acceso a recursos de otros usuarios via ID)
❌ Falta de rate limiting en endpoints sensibles
❌ CORS configurado como "*" en producción
Verificar:
- Cada ruta tiene middleware de auth
- IDs de usuario se validan contra sesión
- Rate limiting en login, registro, reset-password
- CORS whitelist explícita
A02: Cryptographic Failures
Buscar:
❌ Passwords en plaintext o con hash débil (MD5, SHA1)
❌ Tokens/secretos hardcoded en código
❌ HTTP en vez de HTTPS para datos sensibles
❌ JWT sin expiración o con secret débil
❌ Datos sensibles en logs (passwords, tokens, PII)
Verificar:
- Passwords con bcrypt/argon2id (cost factor ≥ 10)
- Secretos en variables de entorno o secret manager
- JWT con expiración razonable (≤ 1h access, ≤ 7d refresh)
- Logs sanitizados (sin PII)
A03: Injection
Buscar:
❌ SQL sin parametrizar (string concatenation)
❌ NoSQL injection (operadores en queries)
❌ Command injection (exec, spawn sin sanitizar)
❌ XSS (innerHTML, dangerouslySetInnerHTML sin sanitizar)
❌ Path traversal (../../../etc/passwd)
❌ LDAP injection, XML injection
Verificar:
- Queries parametrizadas o ORM
- Input sanitizado antes de exec/spawn
- Output encodado en templates
- Paths validados contra whitelist
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.
- 9d ago First seen · 235 lines · 20 tokens per session scan A 27e1e158924f
auditar-seguridad is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 1,860 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 2026-09-03.
Other commands, from other repositories
add-phase
Add phase to end of current milestone in roadmap.
insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.
remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
research-phase
Research how to implement a phase (standalone — usually use /pbr:plan-phase instead).
reapply-patches
Reapply local modifications after a PBR update.
add-todo
Capture idea or task as todo from current conversation context.