Auto Approve Discipline Kit

Run Claude Code unattended with a battle-tested safety framework, hardened deny-rules, and a 6-layer rollback ladder.

Install
cmdop skills install agensi-auto-approve-discipline-kit

The Auto Approve Discipline Kit is a governance framework designed for developers running Claude Code and other terminal-based AI agents in unattended or long-running modes. The core problem it addresses is the tradeoff between auto mode, where agents can perform dangerous operations, and manual mode, where developers must approve every tool call individually. This skill provides configuration patterns and mental models that sit between those extremes.

The framework implements a strict safety layer specifically targeting high-risk operations: accidental file deletions, forced git pushes, and secret leakage. By applying hardened deny-rules, developers can dispatch autonomous agent chains lasting up to 90 minutes without manually approving each of the 50 or more tool calls such a session might generate.

A key component is the 6-layer rollback ladder, which provides structured recovery paths if an agent operation goes wrong. This turns Claude Code from an interactive pair-programmer requiring constant confirmation into an autonomous operator that can be left to run complex, multi-step tasks safely.

This is a skill — it delivers configuration patterns and governance models rather than a running server or callable API. There are no environment variables to configure and no transport layer involved. It is intended for developers who already work with Claude Code or similar terminal-based AI agents and want to harden their automation without sacrificing the ability to run long, uninterrupted workflows.

Use cases

  • Configure deny-rules to block dangerous git operations like force pushes during automated agent runs
  • Dispatch 90-minute multi-agent chains without manually approving each tool call
  • Apply a 6-layer rollback ladder to recover from unintended agent actions
  • Prevent secret leakage during unattended Claude Code sessions
  • Stop runaway agents from deleting or overwriting files unintentionally
  • Transition Claude Code from interactive mode to reliable autonomous operator for long tasks

When to use it

  • Running Claude Code or terminal-based AI agents in unattended auto mode
  • Executing long multi-step agentic workflows where manual approval of every tool call is impractical
  • Hardening an existing Claude Code setup against destructive file or git operations
  • Teams that need governance guardrails before delegating complex tasks to autonomous agents

When not to use it

  • Projects not using Claude Code or a compatible terminal-based AI agent
  • Workflows requiring a callable API or MCP server — this skill provides no tools or endpoints
  • Scenarios where the agent environment cannot accept configuration pattern changes
  • Developers looking for a runtime enforcement system rather than configuration-based guidance