# Enforce Coding-Agent Write and Shell Policies with Probity

> Use Probity when Claude Code, Codex, or GitHub Copilot CLI should be blocked from unsafe file writes or shell commands before they happen.

- Skill: `agentskillexchange/enforce-coding-agent-write-and-shell-policies-with-probity` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/enforce-coding-agent-write-and-shell-policies-with-probity`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/enforce-coding-agent-write-and-shell-policies-with-probity/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/enforce-coding-agent-write-and-shell-policies-with-probity

---


# Enforce Coding-Agent Write and Shell Policies with Probity

Use Probity when Claude Code, Codex, or GitHub Copilot CLI should be blocked from unsafe file writes or shell commands before they happen.

## Prerequisites

Node.js/npm; @nizos/probity package; probity.config.ts; one supported agent host such as Claude Code, Codex, or GitHub Copilot CLI.

## Installation

Install or set up from the source-backed instructions:

Install with npm install -D @nizos/probity, create probity.config.ts with scoped rules such as enforceTdd(), then follow docs/setup.md to wire Probity into Claude Code, Codex, or GitHub Copilot CLI.

- Source: https://github.com/nizos/probity

## Documentation

- https://github.com/nizos/probity

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/enforce-coding-agent-write-and-shell-policies-with-probity/)