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 skills add Mazalucas/El-DT-Lightweight-Army --skill hack-auditgit clone --depth 1 https://github.com/Mazalucas/El-DT-Lightweight-ArmyWrote 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/skills/mazalucas/el-dt-lightweight-army/hack-audit)<a href="https://agentmods.dev/skills/mazalucas/el-dt-lightweight-army/hack-audit"><img src="https://agentmods.dev/badge/skills/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.
<a href="https://agentmods.dev/skills/mazalucas/el-dt-lightweight-army/hack-audit"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/hack-audit.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 | $0.00080 | $0.02070 |
| Opus 5 | $0.00040 | $0.01035 |
| Sonnet 5 | $0.00016 | $0.00414 |
| Haiku 4.5 | $0.00008 | $0.00207 |
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 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocolos DT (heredar)
Subagente del Director Técnico: ordenar, cuestionar, alternativas, Contexto consultado, Puntos ciegos / Mejoras detectadas, post-delegación. Multi-agente: DEFER: <rol>.
Activación
/hack, mención de esta skill o delegación → si el IDE expone subagentes, correr como hack-audit (.cursor/agents/hack-audit.md); si no (Antigravity, Codex), ejecutar este pipeline en la conversación.
Mandato duro (no negociable)
- Sin ofensiva ejecutable — nada de exploits, PoCs, payloads, malware ni comandos de ataque. El escenario se describe en prosa.
- Sin alucinar vulnerabilidades — ningún hallazgo se afirma sin (a) traza del dato desde su origen hasta el sink y (b) búsqueda activa del control que lo desmiente (middleware, rules, validación aguas arriba). Sin traza completa → va a Sospechas, nunca a Confirmados, y no puede ser CRITICAL/HIGH. Detalle:
references/severity-rubric.md. - Evidencia determinista primero — correr los scanners disponibles antes de juzgar a ojo (orden en
references/attack-surface.md§0). El informe lista los comandos ejecutados. - Secretos — nunca pegar el valor: redactar y clasificar por tipo × estado (
severity-rubric.md). Un placeholder no es un incidente. - Higiene del artefacto — el informe nombra tus debilidades: vive gitignoreado en
vitals/work/audits/. Nunca commitearlo ni pegarlo en un issue público. - Anclado al repo — fixes concretos sobre paths reales; nada de teoría OWASP genérica.
Alcance
| Invocación | Alcance |
|---|---|
/hack |
Full repo — los 9 dominios |
/hack auth · api · authz · secrets · data · frontend · infra · arquitectura · agents |
Un dominio |
/hack diff · /hack pr |
Cambios vs base (git diff <base>...HEAD) con contexto: un sink introducido en el diff puede tener su origen fuera del hunk |
| Texto libre | Parsear dominio/paths; si es ambiguo, full |
Repos grandes (fan-out)
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 123 lines · 80 tokens per session scan A 08ce23436bda
hack-audit is a skill published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 2,070 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.
Other skills, from other repositories
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
dale-proof
Verify an existing implementation, fix, migration, deployment, runtime behavior, compatibility boundary, or other technical claim by mapping atomic claims to direct, fresh, reproducible primary signals and returning scoped PROVEN, PARTIAL, UNPROVEN, or CONTRADICTED verdicts with a compact proof capsule. Use when the…
dale-lenses
Reframe an already bounded, difficult engineering, product, operational, or strategic question through one rigorous reasoning lens and at most one genuinely opposing lens, producing a falsifiable model, decision cruxes, and evidence needs instead of a tour of frameworks. Use when the user explicitly invokes…
dale-visualize
Create clear, polished, self-contained HTML visualizations by selecting and adapting task-relevant patterns from Anthropic's html-effectiveness examples. Use when the user invokes $dale-visualize, selects Dale Visualize through /skills, or asks to turn code, architecture, research, plans, comparisons, reports…
world-builder
Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.
dale-graph
Decompose complex work into an adaptive graph of owned outcomes and evidence, using subagents by default. Use for $dale-graph, a requested task graph, or work with independent implementation or proof boundaries.