Release-truth gate for AI-generated code: catches hallucinated APIs, missing imports and claims your code can't back up, before release. Free CLI, GitHub Action and MCP server; PRO and OMEGA add more.
This repository also configures its own agents. See what Agents-Hefesto tells them →
Skill Claude Code
The HefestoAI agent skill moved to skills/hefestoai/ (name: hefestoai, following the Agent Skills specification). Its reference docs (commands.md, issuetypes.md, integration.md, semanticdrift.md, reliabilitydrift.md and analysis/) moved with it.
Skill Claude CodeCodex
Interpret HefestoAI analyze / pre-commit / CI output, suggest fixes, and draft a commit-quality summary. Use after hefesto analyze, after a Hefesto hook or CI gate, or when the user asks what Hefesto found.
Skill Claude Code
Run HefestoAI before committing AI-generated code: pre-commit / CI quality gate for semantic drift, security, and reliability. Use when the user asks about Hefesto, code quality gates, semantic drift, install hooks, or validating Claude/Codex/Cursor output before commit.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: