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.
git clone --depth 1 https://github.com/gonzalezpazmonica/saviaWrote 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/gonzalezpazmonica/savia/ai-exposure-audit)<a href="https://agentmods.dev/commands/gonzalezpazmonica/savia/ai-exposure-audit"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/ai-exposure-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/commands/gonzalezpazmonica/savia/ai-exposure-audit"><img src="https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/ai-exposure-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 | $0.00026 | $0.01256 |
| Opus 5 | $0.00013 | $0.00628 |
| Sonnet 5 | $0.00005 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
ai-exposure-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 5d 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:
- ai-exposure-audit — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ai-exposure-audit — Auditoría de Exposición IA
🦉 Savia mide cuánto de cada rol ya está siendo automatizado vs. cuánto podría estarlo. Fuente: Anthropic "Labor Market Impacts of AI" (2026) — observed exposure framework.
Cargar perfil de usuario
Grupo: Team & Strategy — cargar:
identity.md— nombre, rolprojects.md— proyecto(s)preferences.md— language, detail_levelequipo.md— miembros, roles, seniority
Subcomandos
/ai-exposure-audit— auditoría completa del equipo/ai-exposure-audit --role {rol}— análisis de un rol específico/ai-exposure-audit --team {equipo}— análisis de un equipo/ai-exposure-audit --threshold {N}— solo roles con exposición > N%/ai-exposure-audit reskilling— plan de reconversión por rol
Flujo
Paso 1 — Mapear tareas por rol
Para cada rol del equipo, descomponer en tareas O*NET-style:
- Listar tareas core del rol (6-12 por rol)
- Clasificar cada tarea: cognitive-routine, cognitive-nonroutine, manual
- Asignar peso relativo (% del tiempo dedicado)
Paso 2 — Calcular exposición teórica vs. observada
Para cada tarea:
┌──────────────────────────────────────────────────────────┐
│ EXPOSICIÓN TEÓRICA = ¿Puede la IA hacer esta tarea? │
│ EXPOSICIÓN OBSERVADA = ¿Ya se está automatizando? │
│ GAP DE ADOPCIÓN = Teórica - Observada │
└──────────────────────────────────────────────────────────┘
Escala 0-100 por tarea. Score del rol = media ponderada por peso.
Paso 3 — Clasificar riesgo de desplazamiento
🦉 AI Exposure Audit — {equipo}
Rol | Teórica | Observada | Gap | Riesgo
──────────────|─────────|───────────|──────|────────
Data Entry | 85% | 67% | 18% | 🔴 Alto
QA Manual | 72% | 45% | 27% | 🔴 Alto
Dev Backend | 65% | 33% | 32% | 🟡 Medio
PM/Scrum | 40% | 15% | 25% | 🟢 Bajo
Architect | 30% | 10% | 20% | 🟢 Bajo
🔴 Alto (>60% observada): Desplazamiento activo
🟡 Medio (30-60%): Transición en curso
🟢 Bajo (<30%): Augmentation predominante
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.
- 5d ago First seen · 148 lines · 26 tokens per session scan A 5ab7c88a1f2e
ai-exposure-audit is a command published in the GitHub repository gonzalezpazmonica/savia (50 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 1,256 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 2026-09-06.
Other commands, from other repositories
wtfp:contribute
Guide a bounded WTF-P contribution from branch creation through a reviewable change request.
project-skill
This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments and operates only on the current project.
project-brief
Convert a technical spec into a PM/CTO-readable executive summary. Simplify technical details, focus on business value.
tickets-implement
This is a user-invocable command. Execute it only because the current invocation explicitly selected it. It takes no arguments: every invocation processes the complete current project queue that is ready for implementation.
hive
Query and manage swarm tasks (cells).
status
Check swarm coordination status - workers, messages, reservations.