apoer-agent-guardrail
par uchibeke
Coding Agents & IDEsRésumé
Pre-action authorization for AI agents.
Description
Ce que fait ce skill
APort Agent Guardrail intercepts every tool call an AI agent makes and checks it against a policy before the tool runs. The policy engine is deterministic and fail-closed — if the guardrail errors or denies a call, the tool is blocked. Install once; the OpenClaw plugin enforces policy automatically after that.
The guardrail runs in before_tool_call, so the agent cannot skip or work around it, unlike post-hoc logging or advisory-only checks.
Quand l'utiliser
- Blocking unauthorized shell commands before an agent executes them
- Preventing message sends to unapproved recipients
- Auditing MCP tool calls across automated workflows
- Requiring policy approval before PR creation or merge
- Stopping accidental data exports in production environments
Exemple de workflow
User asks: An AI agent attempts to send a WhatsApp message to an external number
- 1
Agent prepares to call the messaging tool with target number and message content
- 2
APort OpenClaw plugin intercepts the call in before_tool_call
- 3
Guardrail script checks tool name 'messaging.message.send' and context JSON against the local or hosted passport policy
- 4
Policy engine returns ALLOW (exit 0) or DENY (exit 1)
- 5
If denied, the tool is blocked and the reason is written to decision.json
Tool either runs on ALLOW or is blocked, with the denial reason logged to decision.json
Prérequis
- aport.io account and agent_id (optional, required only for hosted passport mode)
Installation
clawhub install uchibeke/apoer-agent-guardrailExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.