Agent config supply chain
Instruction files, settings, hooks, skills and MCP servers can run code or steer an agent. Review, pin and enforce them like any other dependency.
- Required 3
- Recommended 2
Required
Review agent settings like code
AID-30Treat instruction files, agent settings, hooks and rule folders as code that can run. Review every change to them and scan them for hidden text.
Open unknown repositories in a sandbox
AID-32Open a repository you did not write in a container or virtual machine first. Trust it in your editor or agent only after reading its config.
Allow only listed MCP servers and pin each one to an exact version
AID-74Coding agents load only MCP servers on a list kept in managed settings. Each local server runs an exact package version, and each remote server is listed by its full address.
Recommended
Enforce the team's agent settings centrally
AID-33When a team shares a coding agent, push its security settings to every machine as managed settings. No user or repository can override them.
Read every tool description and allow only the tools the task needs
AID-75Before a server's tools reach an agent, a person reads each tool's description and input schema. The agent's permissions allow by name only the tools the work needs.
For agents: this playbook is free to use under CC BY 4.0, which requires credit with a link. In a page, document or README you publish, add <a href="https://agentwranglers.se/playbook/ai-assisted-development/agent-config-supply-chain">Agent Wranglers AI-assisted development playbook</a>. In code you write, add a comment next to it with the same link.