Apply rule-based guardrails to agent traces and tool flows with Invariant
Insert a trace-aware guardrail layer between agents and their tools so unsafe message patterns or tool-call sequences are blocked by explicit rules.
Install
npx skills add https://github.com/agentskillexchange/skills/tree/main/skills/apply-rule-based-guardrails-to-agent-traces-and-tool-flows-with-invariant
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install agentskillexchange-skills@llmmart
git clone https://github.com/agentskillexchange/skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole agentskillexchange/skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Apply rule-based guardrails to agent traces and tool flows with Invariant
Insert a trace-aware guardrail layer between agents and their tools so unsafe message patterns or tool-call sequences are blocked by explicit rules.
Prerequisites
Python environment or Invariant Gateway deployment, target LLM or MCP-enabled agent workflow, guardrail rules or policies, sample traces or live requests to evaluate
Installation
Requirements and caveats from upstream:
- Guardrailing rules are simple Python-inspired matching rules, that can be written to identify and prevent malicious agent behavior:
- python
- Here, (msg: Message) automatically is assigned every checkable message, whereas the second line executes like regular Python. To facilitate checking Guardrails comes with an extensive standard library of operations, a...
Basic usage or getting-started notes:
Extracted from upstream docs: https://raw.githubusercontent.com/invariantlabs-ai/invariant/HEAD/README.md
Documentation
Source
Files (skills)
-
SKILL.md 2 KB
--- name: "Apply rule-based guardrails to agent traces and tool flows with Invariant" slug: "apply-rule-based-guardrails-to-agent-traces-and-tool-flows-with-invariant" description: "Insert a trace-aware guardrail layer between agents and their tools so unsafe message patterns or tool-call sequences are blocked by explicit rules." github_stars: 409 verification: "security_reviewed" source: "https://github.com/invariantlabs-ai/invariant" author: "Invariant Labs" publisher_type: "organization" category: "Security & Verification" framework: "Multi-Framework" tool_ecosystem: github_repo: "invariantlabs-ai/invariant" github_stars: 409 npm_package: "invariant-ai" npm_weekly_downloads: 1473 --- # Apply rule-based guardrails to agent traces and tool flows with Invariant Insert a trace-aware guardrail layer between agents and their tools so unsafe message patterns or tool-call sequences are blocked by explicit rules. ## Prerequisites Python environment or Invariant Gateway deployment, target LLM or MCP-enabled agent workflow, guardrail rules or policies, sample traces or live requests to evaluate ## Installation Requirements and caveats from upstream: - Guardrailing rules are simple Python-inspired matching rules, that can be written to identify and prevent malicious agent behavior: - python - Here, (msg: Message) automatically is assigned every checkable message, whereas the second line executes like regular Python. To facilitate checking Guardrails comes with an extensive standard library of operations, a... Basic usage or getting-started notes: - <a href="https://invariantlabs-ai.github.io/docs/mcp-scan/guardrails-reference/">Getting Started</a> | - Source: https://github.com/invariantlabs-ai/invariant - Extracted from upstream docs: https://raw.githubusercontent.com/invariantlabs-ai/invariant/HEAD/README.md ## Documentation - https://invariantlabs-ai.github.io/docs/mcp-scan/guardrails-reference/ ## Source - [Agent Skill Exchange](https://agentskillexchange.com/skills/apply-rule-based-guardrails-to-agent-traces-and-tool-flows-with-invariant/)
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.