← Browse
guardrails
bharath-gp ★ 0
The guardrails plugin provides five safety-focused capabilities for reviewing Claude's output: blast-radius (impact assessment), secret-sentry (credential detection), reflect (response validation), assumption-tracker (implicit assumption identification), and self-critique (quality and safety review). These tools work as built-in checks to help developers evaluate potential risks and improve response reliability before deployment.
Install
> /plugin marketplace add bharath-gp/ai-harness/tree/HEAD/plugins/guardrails
> /plugin install guardrails
Source: https://github.com/bharath-gp/ai-harness/tree/HEAD/plugins/guardrails
What it's made of
no extra components
- Commands
- 0
- Agents
- 0
- Skills
- 0
- MCP servers
- 0
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
- none
- 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 (bharath-gp).