foundry-agt
OfficialEnforce governance for Foundry agent actions
Authoraiappsgbb
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill prevents Foundry hosted agents from performing unsafe or noncompliant actions by enforcing deterministic, pre-execution policy checks outside the LLM.
Core Features & Use Cases
- Policy Engine for Tool/Action Control: Load YAML policies and evaluate them before tool execution to allow or deny actions.
- Capability Allow/Deny Guardrails: Constrain which tools can be called, with explicit denied capabilities for destructive operations.
- Tamper-evident Audit Trail: Produce hash-chained audit records and support CloudEvents export for compliance workflows.
- Starter Governance Policies: Includes ready-to-use default, HITL gate, and PII-deny policy files for common Foundry governance scenarios.
Quick Start
Use the foundry-agt references and policies by wiring the build_governed_agent factory into your Foundry hosted-agent module and loading the references/policies directory for deterministic allow/deny enforcement.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: foundry-agt Download link: https://github.com/aiappsgbb/awesome-gbb/archive/main.zip#foundry-agt Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.