ForgeCode
Open source terminal coding agent with specialized subagents and 300+ supported models.
Forge CodeHow skills run on ForgeCode
ForgeCode runs in the shell with sub-agents that split research, planning, and execution across a task. Each sub-agent reads the same skill files, so one unvetted SKILL.md can propagate through the whole chain before any change reaches review.
Skill security, assessed
Every public skill in our index is assessed by the Anomity Skill Intelligence engine against its real source: remote code execution, credential and data exfiltration, prompt injection, and unsafe installers.
Govern the skill layer on ForgeCode
Scanning a skill before use tells you what it claims to do. Anomity's Endpoint Sensor sees what agents actually do at runtime: it discovers every skill, agent, and MCP server on the endpoint, and policy can allow, deny, or log the tool calls a skill triggers on ForgeCode and every other agent. Violations route to your SIEM, Slack, email, or Jira with a queryable 90-day audit trail.
Book a 30-minute demo to see your own agent and skill inventory.
