command-approval

Here are 3 public repositories matching this topic...

warc0s / opencode-permission-reviewer

Policy-aware AI permission reviewer for OpenCode V1 and V2. Evaluates tool and command requests, allowing, denying with feedback, or escalating to the user.

security typescript opencode developer-tools human-in-the-loop policy-engine bun permission-system ai-agent llm ai-guardrails opencode-plugin tool-approval permission-review command-approval

Updated Oct 10, 2026
TypeScript

ursuciprian / reflex

Star

Pre-execution risk gate for AI coding agents (Claude Code, Codex, opencode, pi, Hermes). Blocks or asks on risky shell commands, guards against prompt injection in what agents read, escalates to System 2 and a human queue. Optional TypeSafe Jev.

Updated Oct 2, 2026
JavaScript

Phocinae / phocinae-guard

Star

Phocinae command approval gate for AI harnesses (Claude Code / Cline / Codex / Crush / dsh hooks): fail-closed local decision guard

hooks decision-making guardrails local-first agent-security fail-closed small-model command-approval

Updated Oct 9, 2026
Python

Add this topic to your repo

To associate your repository with the command-approval topic, visit your repo's landing page and select "manage topics."

Learn more