ai-exposure-audit

ai-exposure-audit is a command for Claude Code from gonzalezpazmonica/savia. It costs 26 tokens per session (1,256 once invoked), scanned A, original, MIT.

An audit tool that estimates how much of each team role’s work is already being automated by AI and how much could be automated. It also examines possible role changes and retraining needs.

In plain words
What is it for?
Use it to assess a whole team, a specific role, or roles above an exposure threshold, then create a retraining plan.
Why use it?
Teams need a clearer view of which tasks may change, rather than judging AI impact by job title alone. This helps reveal where new skills or reassignment may be needed.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter.

Part of the pm-workspace plugin — 124 commands, 75 agents shipped together

Good fit Use it to assess a whole team, a specific role, or roles above an exposure threshold, then create a retraining plan.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gonzalezpazmonica/savia/ai-exposure-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/gonzalezpazmonica/savia

Made for: Claude Code.

Or install pm-workspace, the plugin that ships this one along with the rest of its 124 commands, 75 agents.

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 ai-exposure-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/gonzalezpazmonica/savia/ai-exposure-audit/github.svg)](https://agentmods.dev/commands/gonzalezpazmonica/savia/ai-exposure-audit)
Your own site
<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.

agentmods 80×15 button for ai-exposure-audit

Your own site · 80×15
<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>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,256 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 $0.00026 $0.01256
Opus 5 $0.00013 $0.00628
Sonnet 5 $0.00005 $0.00251
Haiku 4.5 $0.00003 $0.00126

Measured 5d ago against content hash 5ab7c88a1f2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/ai-exposure-audit.md · 148 lines

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, rol
  • projects.md — proyecto(s)
  • preferences.md — language, detail_level
  • equipo.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:

  1. Listar tareas core del rol (6-12 por rol)
  2. Clasificar cada tarea: cognitive-routine, cognitive-nonroutine, manual
  3. 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

Read the full file on GitHub · 148 lines

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. 5d ago First seen · 148 lines · 26 tokens per session scan A 5ab7c88a1f2e

Subscribe to this mod's changes

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.