---
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), the dependency allowlist (.chock/dependency-allo"
canonical: https://agentpluginsdirectory.com/plugins/protect-agent-config
last-updated: 2026-11-13
---

# 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), the dependency allowlist (.chock/dependency-allowlist.txt) 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 guard refuses shell writes to those paths, a redirect, rm/mv/tee/sed -i, cp into the path, git checkout/restore, PowerShell Set-Content/Add-Content/Out-File; reads and copies out pass, and `chock sync` passes. Best-effort and deliberately coarse. The 'chock: approved-config-change' marker is friction plus an audit trail, not authentication. A second, tool_use-only gate refuses Edit/Write to the same paths; it never runs at commit, so a person stays free to edit them.
## Package we checked
The manifest we fetched is .agents/policies/protect-agent-config/plugin.json in open-coder-ai/chock. The plugin root is the directory that holds that file. Its $schema is https://agent-plugins.org/schemas/1.0.0/plugin.schema.json. The manifest lists 1 skill (protect-agent-config) and no MCP servers. Extension keys: io.github.open-coder-ai.
- Slug: protect-agent-config
- Publisher: chock-core
- Repository: https://github.com/open-coder-ai/chock
- Manifest: .agents/policies/protect-agent-config/plugin.json
- Version: 0.2.0
- License: Apache-2.0
- Category (editorial): security
- Skills: 1 (protect-agent-config)
- MCP servers: 0
- Stars: 10
- Repository created: 2026-08-17
- Repository last pushed: 2026-11-13
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/protect-agent-config
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- 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…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
