Agent Plugins Marketplace
← All plugins

protect-agent-config

v0.2.0

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. [Session-enforced via a PreToolUse hook; needs git, a usable bash and a Python 3.11+ (python3, python or py, whichever actually runs; the Windows Store stub is skipped). With no working Python the hook refuses (exit 2); without git or bash, fail-open clients allow silently and fail-closed clients refuse matched commands. If the guard itself crashes or times out, the hook asks for confirmation rather than allowing silently.]

Claude Code1 Skill

By chock-coreLicense: Apache-2.02 GitHub starsUpdated 6 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 30, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install protect-agent-config for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install protect-agent-config-6@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/open-coder-ai/chock-copilot-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is claude/protect-agent-config/.

Plugin files

claude/protect-agent-config/
├── .claude-plugin/plugin.json
└── skills/protect-agent-config/SKILL.md

Included Skills1

protect-agent-configskills/protect-agent-config/SKILL.md

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.

Plugin manifests1

claude/protect-agent-config/.claude-plugin/plugin.json
{
  "name": "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-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. [Session-enforced via a PreToolUse hook; needs git, a usable bash and a Python 3.11+ (python3, python or py, whichever actually runs; the Windows Store stub is skipped). With no working Python the hook refuses (exit 2); without git or bash, fail-open clients allow silently and fail-closed clients refuse matched commands. If the guard itself crashes or times out, the hook asks for confirmation rather than allowing silently.]",
  "keywords": [
    "chock",
    "policy-as-code",
    "rule",
    "advise",
    "{'control': 'asi03', 'coverage': 'partial', 'note': 'blocks shell self-modification of agent permission and instruction files; identity design and grant scoping remain advisory'}"
  ],
  "version": "0.2.0",
  "author": {
    "name": "chock-core"
  },
  "license": "Apache-2.0",
  "repository": "https://github.com/open-coder-ai/chock-catalog"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[protect-agent-config on Agent Plugins Marketplace](https://pluginsmp.com/plugins/protect-agent-config-6)