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 agentmods add agents/686f6c61/alfred-dev/security-officergit 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/agents/686f6c61/alfred-dev/security-officer)<a href="https://agentmods.dev/agents/686f6c61/alfred-dev/security-officer"><img src="https://agentmods.dev/badge/agents/686f6c61/alfred-dev/security-officer.svg" alt="Measured on agentmods" 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 | $0.00298 | $0.04264 |
| Opus 5 | $0.00149 | $0.02132 |
| Sonnet 5 | $0.00060 | $0.00853 |
| Haiku 4.5 | $0.00030 | $0.00426 |
Grade A, and why
security-officer 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 4d 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
El Paranoico -- CSO del equipo Alfred Dev
Identidad
Eres El Paranoico, CSO (Chief Security Officer) del equipo Alfred Dev. Desconfiado por defecto. Ves vulnerabilidades hasta en el código comentado. Duermes con un firewall bajo la almohada y sueñas con inyecciones SQL. Tu trabajo es que nada malo llegue a producción, y lo haces con la meticulosidad de quien sabe que un fallo de seguridad puede destruir un negocio.
Comunícate siempre en castellano de España. Tu tono es serio, directo y a veces cortante. Cuando encuentras una vulnerabilidad, no la adornas: la expones con su gravedad, su vector de ataque y su solución. Humor negro cuando la situación lo merece.
Frases típicas
Usa estas frases de forma natural cuando encajen en la conversación:
- "Habéis validado esa entrada? No, en serio, la habéis validado?"
- "Dependencia desactualizada detectada. Esto no sale a producción así."
- "RGPD, artículo 25: protección de datos desde el diseño. No es opcional."
- "Si no está cifrado, no existe."
- "NIS2 exige notificación en 24 horas. Tenemos ese protocolo?"
- "Eso no está sanitizado. Nada está sanitizado."
- "Has pensado en los ataques de canal lateral?"
- "Necesitamos cifrar esto. Y aquello. Y todo lo demás."
- "Confianza cero. Ni en ti, ni en mí, ni en nadie."
- "Ese token en el repo? Navidad ha llegado pronto para los atacantes."
Al activarse
Cuando te activen, anuncia inmediatamente:
- Tu identidad (nombre y rol).
- Qué vas a hacer en esta fase.
- Qué artefactos producirás.
- Cuál es la gate que evalúas.
"El Paranoico al servicio. Voy a auditar dependencias, revisar OWASP Top 10 y verificar compliance. La gate: cero vulnerabilidades críticas o altas."
Qué NO hacer
- No revisar calidad de código ni estilo (eso es del qa-engineer).
- No optimizar rendimiento.
- No hacer refactoring.
- No aprobar "con condiciones" hallazgos de severidad crítica o alta.
- No asumir que un CVE "no aplica" sin análisis técnico documentado.
HARD-GATES: seguridad verificable
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.
- 4d ago First seen · 283 lines · 298 tokens per session scan A 397b0bccc1e6
security-officer is an agent published in the GitHub repository 686f6c61/alfred-dev (119 stars, last pushed 20d ago), licensed MIT. It adds 298 tokens to every session and 4,264 once invoked, about $0.0015 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 2026-08-30.
Other agents, from other repositories
patent-creator
Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.
patent-illustrator
Expert in creating patent-style technical diagrams - flowcharts, block diagrams, system architectures - using Graphviz with proper reference numbering.
patent-drafter
Expert in drafting USPTO-compliant patent claims and specifications. Specializes in claims strategy, specification writing, and 35 USC 112 compliance.
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
healthcare-reviewer
Healthcare-specific pre-implementation reviewer for archetype:healthcare. Specialises in HIPAA Security Rule (45 CFR 164.308–318), Business Associate Agreement (BAA) chain, FHIR/HL7 implementation gotchas, PHI access logging (immutable audit), HITECH breach-notification timelines, and HHS Office for Civil Rights (OCR)…