---
title: "protect-agent-config"
description: "Guard against an agent hand-editing its own guardrails. Agent instruction files (AGENTS.md and the per-agent wrappers), permission files (.claude/settings.json, .mcp.json) and vendored enforcement (.chock/bin/, .chock/co"
canonical: https://agentpluginsdirectory.com/plugins/protect-agent-config--open-coder-ai-org
last-updated: 2026-09-08
---

# protect-agent-config
Guard against an agent hand-editing its own guardrails. Agent instruction files (AGENTS.md and the per-agent wrappers), permission files (.claude/settings.json, .mcp.json) and vendored enforcement (.chock/bin/, .chock/compiled/) define what the agent may do -- so a shell command that rewrites them is the agent modifying its own authority (MITRE ATLAS AML.T0081; the AIVSS self-modification factor). The guard refuses shell write-commands targeting those paths; reads pass, and regeneration through `chock sync` passes because the tool writes them itself rather than through shell editing. Best-effort and deliberately coarse: a compound command that both reads a protected file and writes elsewhere may be refused -- rewrite it in two steps. Escape for a human-approved change: include 'chock: approved-config-change' in the command.
- Slug: protect-agent-config--open-coder-ai-org
- Publisher: chock-core
- Repository: https://github.com/open-coder-ai-org/chock
- Manifest: .agents/policies/protect-agent-config/plugin.json
- Version: 0.0.1
- License: Apache-2.0
- Category (editorial): other
- Skills: 1 (protect-agent-config)
- MCP servers: 0
- Stars: 3
- Listing: https://agentpluginsdirectory.com/plugins/protect-agent-config--open-coder-ai-org
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json