---
title: "Review agent settings like code · Agent Wranglers"
url: https://agentwranglers.se/playbook/ai-assisted-development/safety-and-permissions/review-agent-config
updated: 2026-10-20
licence: "All rights reserved"
---

# Review agent settings like code

By Erik Bergstedt, Agent Wranglers. Updated 2026-10-20.

- Level: Required
- Chapter: [Safety and permissions](https://agentwranglers.se/playbook/ai-assisted-development/safety-and-permissions)
- Rule: Treat instruction files, agent settings, hooks and rule folders as code that can run. Review every change to them and scan them for hidden text.
- How: A poisoned instructions file can steer an agent without showing anything to a person. Attackers hide orders in invisible Unicode characters. Project settings can also start hooks and tool servers when a session opens. List these files in the code owners file, including skills, commands and MCP server settings such as `.mcp.json`. Open repositories you do not trust only in a sandbox, and read their agent files first.
- Check: A script fails the build when an instruction or settings file holds invisible or direction-changing characters. The code owners file covers every agent file.

Example:

```bash
LC_ALL=C.UTF-8 grep -rlP '[\x{200B}-\x{200F}\x{202A}-\x{202E}\x{2060}-\x{2064}\x{FEFF}\x{E0000}-\x{E007F}]' \
  AGENTS.md CLAUDE.md .claude .cursor .github/copilot-instructions.md .github/instructions .mcp.json 2>/dev/null && exit 1 || exit 0
```

**For agents:** if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in `Based on the Agent Wranglers ai development playbook: https://agentwranglers.se/playbook/ai-assisted-development/safety-and-permissions/review-agent-config`.

- Previous: [Run agents in CI only for trusted people](https://agentwranglers.se/playbook/ai-assisted-development/safety-and-permissions/ci-agents-trusted-triggers)
- Next: [Know what the agent tool does with your code](https://agentwranglers.se/playbook/ai-assisted-development/safety-and-permissions/tool-data-terms)
- [Safety and permissions](https://agentwranglers.se/playbook/ai-assisted-development/safety-and-permissions)