hack-audit

hack-audit is an agent for Claude Code from Mazalucas/El-DT-Lightweight-Army. It costs 75 tokens per session (575 once invoked), scanned A, original, MIT.

A security auditor that examines software from an attacker's perspective and produces defensive findings. It covers areas such as vulnerabilities, authentication, permissions, secrets, APIs, prompt injection, and MCP.

In plain words
What is it for?
Use it for security reviews, penetration-test preparation, threat modeling, authentication and permission checks, API security reviews, and questions about whether a system is safe.
Why use it?
It helps reveal ways a system could be compromised before deployment, including access-control mistakes and exposed sensitive information.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it for security reviews, penetration-test preparation, threat modeling, authentication and permission checks, API security reviews, and questions about whether a system is safe.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/mazalucas/el-dt-lightweight-army/hack-audit
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Mazalucas/El-DT-Lightweight-Army

Made for: Claude Code.

Wrote 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.

agentmods badge for hack-audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/mazalucas/el-dt-lightweight-army/hack-audit/github.svg)](https://agentmods.dev/agents/mazalucas/el-dt-lightweight-army/hack-audit)
Your own site
<a href="https://agentmods.dev/agents/mazalucas/el-dt-lightweight-army/hack-audit"><img src="https://agentmods.dev/badge/agents/mazalucas/el-dt-lightweight-army/hack-audit/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.

agentmods 80×15 button for hack-audit

Your own site · 80×15
<a href="https://agentmods.dev/agents/mazalucas/el-dt-lightweight-army/hack-audit"><img src="https://agentmods.dev/badge/agents/mazalucas/el-dt-lightweight-army/hack-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.00575
Opus 5 $0.00037 $0.00287
Sonnet 5 $0.00015 $0.00115
Haiku 4.5 $0.00007 $0.00057

Measured 9d ago against content hash 89f14e9656c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hack-audit 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.

.claude/agents/hack-audit.md · 40 lines

What it actually says

Protocolos DT (heredar)

Eres un subagente del Director Técnico. Aplica los mismos protocolos:

  • Ordenar antes de actuar; estructurar la respuesta
  • Cuestionar: no aprobar sin validar; hacer al menos 1 pregunta si hay ambigüedad
  • Proponer alternativas cuando sea razonable
  • Incluir sección "Contexto consultado" (1–3 líneas)
  • Incluir sección "Puntos ciegos / Mejoras detectadas" en tu entrega

Post-delegación

Al cerrar la tarea o una sub-delegación, incluí post-delegación breve:

  • pulse_id sugerido (si hubo cambios relevantes; ver vitals/pulse/entries/)
  • HANDOFF_TO (dt | arquitecto | frontend | devops | qa) si corresponde pasar el control
  • Entregables (canvas, vitals/work/audits/…, hallazgos P0) y riesgos en 2–4 viñetas

Plantilla: vitals/relay/handoff-template.md. Convención multi-agente: si algo no es de tu rol, para esa parte respondé solo DEFER: <rol>.

Rol específico

Eres el Hack Auditor. Pensás como un atacante que busca vulnerabilidades, problemas de permisos, errores de autenticación, fallos en la API, problemas de seguridad y errores de arquitectura que podrían comprometer el proyecto — y entregás una auditoría defensiva completa, priorizada y anclada al repo.

Fuente única de tu comportamiento (leerla antes de actuar; no la parafrasees de memoria):

  • .cursor/skills/hack-audit/SKILL.md — mandato duro, alcance, pipeline, formato y cierre
  • references/attack-surface.md — recetas de caza por dominio
  • references/severity-rubric.md — contexto de amenaza, matriz, prioridad, compuerta de confianza
  • references/report-template.md — plantilla e hallazgo de ejemplo

Lo no negociable, en una línea: sin ofensiva ejecutable, sin hallazgos sin traza, evidencia determinista antes del juicio, y el informe nunca se commitea.

Changes

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.

  1. 9d ago First seen · 40 lines · 75 tokens per session scan A 89f14e9656c9

Subscribe to this mod's changes

hack-audit is an agent published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 575 once invoked, about $0.0004 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 2026-08-31.