ivan-pinatti-labs

Agent Policy — Development skill for Claude Code

Development community

One command policy for coding agents (Claude Code and Codex): severity-tiered allow/ask/deny rules, a shared guard hook, a sandbox layer and a scratchpad helper.

How to install Agent Policy

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ivan-pinatti-labs/agent-policy and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Policy does

One command policy for coding agents (Claude Code and Codex): severity-tiered allow/ask/deny rules, a shared guard hook, a sandbox layer and a scratchpad helper.

Alternatives in Development

  • Obsidian Health — Run a vault health check — grouped by severity, detects contradictions, concept gaps, stale claims, and struct 277 ★
  • Openshell Deepagent — A general-purpose coding agent that runs inside an NVIDIA OpenShell sandbox, orchestrated by Deep Agents and p 187 ★
  • Incident Commander — Incident Commander - structured incident response with severity assessment and blameless post-mortems 127 ★

README

agent-policy

[![License](https://img.shields.io/github/license/ivan-pinatti-labs/agent-policy?logo=Github&style=for-the-badge)](LICENSE.md) [![GitHub issues](https://img.shields.io/github/issues-raw/ivan-pinatti-labs/agent-policy?logo=Github&style=for-the-badge)](https://github.com/ivan-pinatti-labs/agent-policy/issues) [![GitHub Sponsors](https://img.shields.io/github/sponsors/ivan-pinatti?logo=Github&style=for-the-badge)](https://github.com/sponsors/ivan-pinatti) [![GitHub Repo stars](https://img.shields.io/github/stars/ivan-pinatti-labs/agent-policy?logo=Github&style=for-the-badge)](https://github.com/ivan-pinatti-labs/agent-policy) [![GitHub forks](https://img.shields.io/github/forks/ivan-pinatti-labs/agent-policy?logo=Github&style=for-the-badge)](https://github.com/ivan-pinatti-labs/agent-policy/forks) [![CodeRabbit Pull Request Reviews](https://img.shields.io/coderabbit/prs/github/ivan-pinatti-labs/agent-policy?utm_source=oss&utm_medium=github&utm_campaign=ivan-pinatti-labs%2Fagent-policy&labelColor=171717&color=FF570A&label=CodeRabbit+Reviews&style=for-the-badge)](https://coderabbit.ai) [![SonarQube Quality Gate](https://img.shields.io/sonar/quality_gate/ivan-pinatti-labs_agent-policy?server=https%3A%2F%2Fsonarcloud.io&logo=sonarqubecloud&style=for-the-badge)](https://sonarcloud.io/project/overview?id=ivan-pinatti-labs_agent-policy)

One command policy for coding agents, written once and installed for **Claude Code** (every profile) and **Codex**. Every command the policy lists carries a severity, and the severity decides what the agent does:

Severity Decision Examples
read, low allow reading anyt