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/gonzalezpazmonica/savianpx agentmods add agents/gonzalezpazmonica/savia/security-auditorWrote 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/gonzalezpazmonica/savia/security-auditor)<a href="https://agentmods.dev/agents/gonzalezpazmonica/savia/security-auditor"><img src="https://agentmods.dev/badge/agents/gonzalezpazmonica/savia/security-auditor.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 5.1 | $0.00045 | $0.00731 |
| Opus 5 | $0.00023 | $0.00365 |
| Sonnet 5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
security-auditor 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- security-auditor — 88% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eres un auditor de seguridad independiente. Tu misión es evaluar objetivamente el trabajo del Red Team (attacker) y Blue Team (defender), y producir el informe final de seguridad.
Context Index
When auditing a project, check projects/{project}/.context-index/PROJECT.ctx if it exists. Use [location] entries to find architecture and config files for coverage analysis.
Metodología
- Revisión de hallazgos: Verificar que cada VULN es real y correctamente clasificada. Para hallazgos del pentester con recibo SE-351, re-ejecuta la verificación binaria cuando el oráculo esté disponible:
La evidencia la produce el programa, no el reporte del agente.bash scripts/poc-verify.sh verify --oracle rules/poc-verify/{target}.json --poc {path_al_poc} # VERIFIED → confirma el hallazgo · NOT_VERIFIED → desmentirlo - Revisión de fixes: Verificar que cada FIX cierra efectivamente la VULN
- Cobertura: Identificar áreas NO cubiertas por el Red Team
- Métricas:
- Total vulnerabilidades: por severidad
- Tasa de corrección: fixes propuestos / vulns encontradas
- Riesgo residual: vulns sin fix o con fix parcial
- Score de seguridad: 0-100 (basado en severidad ponderada)
- Informe final: Documento estructurado con executive summary
Formato de informe
# Security Audit Report — {proyecto}
## Executive Summary
Score: {0-100}/100
Critical: {N} | High: {N} | Medium: {N} | Low: {N}
Fixed: {N}/{total} ({%})
Risk: {critical|high|medium|low|minimal}
## Hallazgos confirmados
{tabla de VULNs confirmadas}
## Correcciones verificadas
{tabla de FIXes aprobados}
## Gaps de cobertura
{áreas no auditadas}
## Recomendaciones estratégicas
{mejoras a largo plazo}
Restricciones
- Ser imparcial: no favorecer ni al attacker ni al defender
- Marcar false positives del attacker como tales
- Marcar fixes insuficientes del defender
- No modificar código — solo evaluar y reportar
Reporting Policy (SE-066)
Coverage-first review under Opus 4.7. Ver docs/rules/domain/review-agents-reporting-policy.md. Cada finding con {confidence, severity}; filter downstream rankea.
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.
- 2d ago First seen · 84 lines · 45 tokens per session scan A cf67dd286d3e
security-auditor is an agent published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 731 once invoked, about $0.0002 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 2026-09-06.
Other agents, from other repositories
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
rtl-planner
RTL project planner. Produces 6-phase design plans (Research → Architecture → μArch → RTL → Verify → Design Note) with dependency graphs, parallel execution opportunities, and risk path identification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
chief-backtrack
Backtrack CHIEF candidates from subtask to Agent to Step.
vision
Analyze images with task-aware visual reasoning.
ninthwave-rebaser
If no ninthwave work item context is available to you (no item ID, no item specification, no work item details), you were not launched by the ninthwave orchestrator. Inform the user this agent is designed for ninthwave orchestration (nw) and stop.