guard
TracineHQ contributors v1.5.0
PreToolUse hooks for Claude Code that deny dangerous shell, git, and credential commands before they run: `rm -rf /` shapes, `git push --force`, `python -c` / `node -e` eval, pipe-to-shell, live cr...
From the developer
License
Apache-2.0
Works with
Claude Code
Description
From the marketplace listing
PreToolUse hooks for Claude Code that deny dangerous shell, git, and credential commands before they run: `rm -rf /` shapes, `git push --force`, `python -c` / `node -e` eval, pipe-to-shell, live credentials (`gh auth token`, `aws sts get-session-token`, `op read`), `git -c core.hooksPath=…` injection, silent commit reuse (`git commit -C HEAD~1`, `--reuse-message`). Each deny names the rule and prints a one-line override (`guard allowlist allow-command …`); decisions stream to a JSONL log the optional CLI reads (`pipx install tracine-guard`, then `guard noisy --since 24h` or `guard trace <session>`). Apache-2.0, no third-party deps. Defense in depth alongside Claude Code's own permissions — especially valuable for autonomous agent windows where no human is present to answer an ASK, so denies act as a hard floor. Not a sandbox or exfiltration boundary; see SECURITY.md.
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Security guard hook for Claude Code. Evaluates every tool call (Bash, Edit, Write, Read, MCP) against 864 pattern-matching rules to block...
Shared terms: hook, code, credential, dangerous
-
Pre-execution safety layer that blocks dangerous shell commands and credential file reads using pattern matching + LLM analysis. Fail-clo...
Shared terms: credential, dangerous, shell, command
-
Cync backs up and syncs your Claude Code settings to any Git repository. Push your ~/.claude/ configuration from one machine and pull it...
Shared terms: git, push, command, code
-
Skill Safety Auditor is a Claude Code skill that audits third-party skills for security risks before or after you install them. It runs 1...
Shared terms: credential, shell, command, code
-
An output style + Python hooks that make Claude Code listen before it codes. Asks the right questions, recommends with reasoning, and wri...
Shared terms: python, hook, code, decision
Keywords
Files & skills
guard · catalog manifest
Saved declaration
{}
guard · catalog manifest
Saved declaration
{
"name": "guard",
"source": {
"sha": "aa18d9bf1d5f98b65ca30f85c96f78dff6c7480c",
"url": "https://github.com/TracineHQ/guard.git",
"source": "url"
},
"homepage": "https://github.com/TracineHQ/guard",
"description": "PreToolUse hooks for Claude Code that deny dangerous shell, git, and credential commands before they run: `rm -rf /` shapes, `git push --force`, `python -c` / `node -e` eval, pipe-to-shell, live credentials (`gh auth token`, `aws sts get-session-token`, `op read`), `git -c core.hooksPath=…` injection, silent commit reuse (`git commit -C HEAD~1`, `--reuse-message`). Each deny names the rule and prints a one-line override (`guard allowlist allow-command …`); decisions stream to a JSONL log the optional CLI reads (`pipx install tracine-guard`, then `guard noisy --since 24h` or `guard trace <session>`). Apache-2.0, no third-party deps. Defense in depth alongside Claude Code's own permissions — especially valuable for autonomous agent windows where no human is present to answer an ASK, so denies act as a hard floor. Not a sandbox or exfiltration boundary; see SECURITY.md."
}
guard · catalog manifest
Saved declaration
{
"name": "guard",
"author": {
"url": "https://github.com/TracineHQ",
"name": "TracineHQ contributors"
},
"license": "Apache-2.0",
"version": "1.5.0",
"homepage": "https://github.com/TracineHQ/guard",
"keywords": [
"safety",
"hooks",
"guardrails",
"bash",
"git",
"credentials",
"claude-code-plugin"
],
"repository": "https://github.com/TracineHQ/guard",
"description": "Safety hooks for Claude Code (rm -rf, credential exfil, force-pushes, protected files, subagent scope) with a queryable JSONL decision log."
}
plugin.json observed Nov 6, 2026 · 10:44 UTC. Manifest source ↗
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install guard@claude-community
Technical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 7, 2026 · 00:08 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.