# Inhibit

> Inhibitory control (rIFG). Invocala PRIMA di azioni irreversibili o ad alto blast radius — commit, push, force-push, rm, delete, deploy, send message, hardware print, MCP call mutativa, modifica di state shared. Use BEFORE any irreversible action to pause and verify the impulse is justified. Triggers anche su "voglio fare X" / "procedo" / quando rilevi tu stesso un impulso ad agire rapidamente.

- **Type:** Skill
- **Install:** `agentstack add skill-tommasobbianchi-claude-cognitive-skills-inhibit`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [tommasobbianchi](https://agentstack.voostack.com/s/tommasobbianchi)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [tommasobbianchi](https://github.com/tommasobbianchi)
- **Source:** https://github.com/tommasobbianchi/claude-cognitive-skills/tree/main/skills/inhibit

## Install

```sh
agentstack add skill-tommasobbianchi-claude-cognitive-skills-inhibit
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Inhibit — rIFG (controllo inibitorio)

**Principio**: prima di un'azione irreversibile, sospendi il riflesso "ho già il prossimo passo in mente, lo faccio". Inserisci una pausa di valutazione.

1. **L'azione è irreversibile o ad alto costo di rollback?** (commit pushato, rm, deploy, hardware, messaggio inviato, push remoto). Se no, procedi.
2. **Hai un motivo esplicito ora?** Non "perché è il prossimo passo del piano", ma "perché serve allo scopo X dichiarato".
3. **Conosci lo stato attuale dell'oggetto** che stai per toccare? (Vedi REGOLA HARDCODED CORE.)
4. **L'utente ha autorizzato esplicitamente** questa classe di azione? Se è la prima volta nella sessione, conferma.

Se uno qualunque è NO → fermati. Chiedi o ispeziona. Poi riconsidera.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [tommasobbianchi](https://github.com/tommasobbianchi)
- **Source:** [tommasobbianchi/claude-cognitive-skills](https://github.com/tommasobbianchi/claude-cognitive-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-tommasobbianchi-claude-cognitive-skills-inhibit
- Seller: https://agentstack.voostack.com/s/tommasobbianchi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.