From aport-guardrails
Sets up APort guardrails for Claude Code by creating a passport and activating PreToolUse hook to enforce policies on tool calls. Local evaluation by default, zero network calls.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aport-guardrails:claude-codeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are setting up APort Agent Guardrails for Claude Code. Follow these steps in order.
You are setting up APort Agent Guardrails for Claude Code. Follow these steps in order.
Run these checks. If either fails, tell the user what to install and stop.
bash --version | head -1
Expected: GNU bash, version 4 or higher.
jq --version
Expected: jq-1.x. If missing, tell the user: brew install jq (macOS) or apt install jq (Linux).
${CLAUDE_PLUGIN_ROOT}/bin/aport-status.sh 2>/dev/null
If this prints passport info, guardrails are already active. Ask the user if they want to reconfigure. If they say no, stop here.
If it prints nothing or errors, continue to Step 3.
APORT_FRAMEWORK=claude-code ${CLAUDE_PLUGIN_ROOT}/bin/aport-create-passport.sh --framework=claude-code
This is an interactive wizard. It will prompt the user for:
Let the user interact with the wizard directly. Do not answer the prompts for them.
Expected outcome: A passport file is created at ~/.claude/aport/passport.json.
${CLAUDE_PLUGIN_ROOT}/bin/aport-status.sh
Expected: Shows passport location, agent ID, and evaluation mode. If this succeeds, tell the user guardrails are active.
The PreToolUse hook is registered automatically by the plugin system. No settings.json editing is needed.
If the wizard fails or status shows no passport:
~/.claude/aport/ directory exists~/.claude/DEBUG_APORT=1 prefix for verbose outputnpx claudepluginhub aporthq/aport-agent-guardrails --plugin aport-guardrailsSets up APort guardrails for OpenClaw to enforce local-first policies on tool calls via passport checks before execution. Zero network calls by default.
Enforces tiered runtime guardrails on Claude Code agent actions: auto-approves reads/routines, notifies on writes/commits, requires approval for installs/emails/deletes, blocks credential leaks/sudo. Logs audits.
Enforces runtime security policies on Claude Code actions via Pre/PostToolUse hooks, blocks dangerous shell commands/file ops/MCP calls, scans configs for OWASP ASI10 vulnerabilities, logs audit trails.