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.

Agent Plugins1 Skill

By chock-coreLicense: Apache-2.08 GitHub starsUpdated yesterday

Directory evidence

Runtimes: Agent Plugins
Parsed components: 1 skill or MCP entry
Source updated: Oct 3, 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 →

Get the plugin

$ git clone https://github.com/open-coder-ai/chock

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

This listing currently publishes only the generic Agent Plugins format. Automatic install commands for other clients are not generated yet.

Plugin files

.agents/policies/protect-agent-config/

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

Included Skills1

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

Plugin manifests1

.agents/policies/protect-agent-config/plugin.json

{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "protect-agent-config",
  "version": "0.2.0",
  "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.",
  "author": {
    "name": "chock-core"
  },
  "repository": "https://github.com/open-coder-ai/chock-catalog",
  "license": "Apache-2.0",
  "keywords": [
    "chock",
    "policy-as-code",
    "rule",
    "advise",
    "asi03"
  ],
  "extensions": {
    "io.github.open-coder-ai": {
      "manifest": "manifest.yaml",
      "artifact": "rule",
      "enforcement": "advise",
      "coverage_without_chock": "advisory"
    }
  }
}

Browse the “chock” tag →

agent-discipline

by chock-core

trigger: edits without reading, unverified completion claims, weakened tests, dead code. avoid: skipping verification, deleting assertions, leaving unused code.

Agent Plugins1 Skill

8Updated yesterday

block-destructive-commands

by chock-core

Best-effort guard against destructive commands, read as parsed commands (bash -c and cd chains included, echo excluded): rm -rf on absolute, home ($HOME/~) or root-adjacent paths (and PowerShell Remove-Item -Recurse); git push --force (not --force-with-lease), reset --hard, clean -f; kubectl delete; terraform destroy; aws s3 rm --recursive / rb --force; dropdb; helm uninstall/delete; docker volume rm/prune and system prune; gcloud ... delete; find -delete / -exec rm; shred; truncate; wipefs -a. git branch -D asks first. Verbs are matched position-aware, so a bucket or object NAMED like a verb is allowed, and a relative path in the working tree stays allowed. sudo, doas and pkexec are transparent. A pre-push hook refuses any non-fast-forward push -- force, +refspec or lease alike; a human escapes with git push --no-verify. Known bypasses: aliases, an unusual value-flag, interpreters and scripts. Friction, not a security boundary.

Agent Plugins1 Skill

8Updated yesterday

block-invisible-unicode

by chock-core

The mechanizable slice of prompt-injection defense, enforced at two points: at commit (the git hook, over staged changes) and at agent tool-use (over a tool call's arguments, as the agent writes) -- invisible and direction-override Unicode. Bidi controls make code read differently than it parses (Trojan Source, CVE-2021-42574); Unicode tag-block characters smuggle instructions that are invisible to a human reviewer but fully legible to the agent reading the file. Zero-width joiners and bidi marks (ZWJ/ZWNJ/LRM/RLM) are deliberately NOT matched -- they are legitimate in emoji sequences and in Persian, Arabic and Indic text -- so ordinary internationalised content passes; only the override/embed/isolate controls and the tag block, which have no honest use in a source tree, are blocked. Escape: 'pragma: allowlist invisible-unicode' on the same line.

Agent Plugins1 Skill

8Updated yesterday

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-3)

Directory evidence

Get the plugin

Plugin files

Included Skills1

Plugin manifests1

Related plugins

For maintainers

Related plugins