guard

v0.5.2

Turn coding rules into harness-enforced ones. comment-guard hands back every comment block an edit added or grew, three lines or longer, with one question: is this why, or is this what?

CodexClaude Code

By QLicense: MIT1 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 0 skill or MCP entries
Source updated: Sep 29, 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 guard for Codex and Claude Code

Installs for the current user

codex plugin marketplace add FunnyQ/cc-plugins
codex plugin marketplace upgrade q-lab-marketplace
codex plugin add guard@q-lab-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the q-lab-marketplace catalog, then install this plugin.

Compatibility: the page URL and API slug “guard-3” remain stable.

Codex: guard-3@agent-plugin-marketplace → guard@q-lab-marketplace

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/FunnyQ/cc-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is packages/guard/.

Plugin files

packages/guard/

├── .codex-plugin/plugin.json
└── .claude-plugin/plugin.json

Plugin manifests2

packages/guard/.codex-plugin/plugin.json

{
  "name": "guard",
  "version": "0.5.2",
  "description": "Turn coding rules into harness-enforced ones. comment-guard hands back every comment block an edit added or grew, three lines or longer, with one question: is this why, or is this what?",
  "author": {
    "name": "Q"
  },
  "license": "MIT",
  "keywords": [
    "guard",
    "hook",
    "comment",
    "why-not-what",
    "coding-discipline",
    "lint",
    "code-quality"
  ]
}

packages/guard/.claude-plugin/plugin.json

{
  "name": "guard",
  "version": "0.5.2",
  "description": "Turn coding rules into harness-enforced ones. comment-guard hands back every comment block an edit added or grew, three lines or longer, with one question: is this why, or is this what?",
  "author": {
    "name": "Q"
  },
  "license": "MIT",
  "keywords": [
    "guard",
    "hook",
    "comment",
    "why-not-what",
    "coding-discipline",
    "lint",
    "code-quality"
  ],
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Edit|Write",
        "hooks": [
          {
            "type": "command",
            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/hooks/comment-guard.ts\"",
            "timeout": 10
          }
        ]
      }
    ],
    "UserPromptSubmit": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/hooks/comment-sweep.ts\" snapshot",
            "timeout": 10
          }
        ]
      }
    ],
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "bun \"${CLAUDE_PLUGIN_ROOT}/hooks/comment-sweep.ts\" sweep",
            "timeout": 10
          }
        ]
      }
    ]
  }
}

Browse the “guard” tag →

malicious-skill-plugin

by Hashgraph Online

Fixture with a dangerous local skill definition

Codex1 Skill

676Updated 2 hours ago

guardrails

by Melodic Software

Fifteen safety guards that block secret/credential writes, hardcoded machine-specific paths, git hook-bypass attempts, irreversible git operations (force-push, reset --hard, worktree-wide checkout/restore discards), Bash file-write workarounds that circumvent Write/Edit hooks, Windows drive-root /tmp writes (POSIX /tmp, C:\tmp, \tmp), an EXPORTED MSYS_NO_PATHCONV / MSYS2_ARG_CONV_EXCL that unconverts a later path argument on Windows, a Bash recursive `rm` whose target normalizes to a filesystem root (`/`, the MSYS-translated bare backslash, `~`, `$HOME`, a drive root such as `C:\` or `/c`, a WSL or cygdrive mount root), that carries `--no-preserve-root`, that names an empty or bare-variable operand, or that resolves outside the session's git tree, temp directories and scratchpad (Bash only; PowerShell `Remove-Item -Recurse` is not covered), multi-line `git commit -m` messages (an actual-newline `-m` mangles across shells; single-line `-m` passes), commit subjects and gh pr create titles that violate the repo's tracked team convention (when one is declared in .claude/source-control.md), (advisory) hallucinated CLI flags, (advisory) /plugin:skill references that do not resolve, (advisory) markdown citing a repo path the repo's own history shows was removed, (advisory, opt-in) un-throttled Workflow fan-out that risks burst 529s, and (advisory, opt-in) direct gh pr create calls bypassing this marketplace's own pull-request skill. Each guard is independently toggleable.

Claude Code1 Skill

20Updated yesterday

stop-phrase-guard

by Craig Motlin

Stop hook that catches ownership-dodging and session-quitting phrases and forces the assistant to keep working

CodexClaude Code

15Updated last month

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.

[guard on Agent Plugins Marketplace](https://pluginsmp.com/plugins/guard-3)