← Browse
guardrails
Rene-Roscher ★ 0
This Claude Code plugin enforces two core safety rules through hooks: stopping after ten failed fix attempts and preventing commands that skip or silence checks. It tracks failed shell commands, distinguishes read-only probes from actual attempts, and blocks bypass patterns like --no-verify and HUSKY=0.
Install
> /plugin marketplace add Rene-Roscher/skills/tree/HEAD/plugins/guardrails
> /plugin install guardrails
Source: https://github.com/Rene-Roscher/skills/tree/HEAD/plugins/guardrails
What it's made of
3 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 0
- MCP servers
- 0
- Hooks
- 3 · PostToolUse, PreToolUse, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
python3- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (Rene-Roscher).