---
title: "Agent config supply chain · Agent Wranglers"
url: https://agentwranglers.se/playbook/ai-assisted-development/agent-config-supply-chain
parts: 5
tokens_total: 4884
updated: 2026-10-27
build: a2a6bdfed830
tokens: 766
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Agent config supply chain

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [AI-assisted development](https://agentwranglers.se/playbook/ai-assisted-development.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-27.

> Instruction files, settings, hooks, skills and MCP servers can run code or steer an agent. Review, pin and enforce them like any other dependency.

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/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.

## Required

- AID-30 [Review agent settings like code](https://agentwranglers.se/playbook/ai-assisted-development/agent-config-supply-chain/review-agent-config.md) · 875 tokens · updated 2026-10-27
  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.
- AID-32 [Open unknown repositories in a sandbox](https://agentwranglers.se/playbook/ai-assisted-development/agent-config-supply-chain/untrusted-repositories.md) · 729 tokens · updated 2026-10-27
  Open 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.
- AID-74 [Allow only listed MCP servers and pin each one to an exact version](https://agentwranglers.se/playbook/ai-assisted-development/agent-config-supply-chain/mcp-server-allow-list.md) · 1,297 tokens · updated 2026-10-27
  Coding 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

- AID-33 [Enforce the team's agent settings centrally](https://agentwranglers.se/playbook/ai-assisted-development/agent-config-supply-chain/managed-agent-settings.md) · 1,095 tokens · updated 2026-10-27
  When a team shares a coding agent, push its security settings to every machine as managed settings. No user or repository can override them.
- AID-75 [Read every tool description and allow only the tools the task needs](https://agentwranglers.se/playbook/ai-assisted-development/agent-config-supply-chain/mcp-tool-review.md) · 888 tokens · updated 2026-10-27
  Before 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.

- Previous: [Isolation and credentials](https://agentwranglers.se/playbook/ai-assisted-development/isolation-and-credentials.md)
- Next: [Apps built with AI builders](https://agentwranglers.se/playbook/ai-assisted-development/apps-built-with-ai-builders.md)
- [All chapters](https://agentwranglers.se/playbook/ai-assisted-development.md)