executionlayersecurity skills

canyonroad/agentsh

Skill Claude CodeCodex

dangerous eval pattern.

canyonroad/agentsh

Skill Claude CodeCodex

Use when creating a new AgentSH security policy, including agent sandboxes, CI pipelines, development environments, HTTP service gateways, or Postgres-family database access policies.

canyonroad/agentsh

Skill Claude CodeCodex

Use when adding, removing, or updating rules in an existing AgentSH policy, modifying security permissions, HTTP service declarations, Postgres-family database rules, resource limits, or policy YAML files.