Audit everything after anything. Single-command AI agent skill that audits a codebase end to end and emits a scored, evidence-backed audit report (AUDIT.mdx) with an agent-executable remediation plan. Claude Code, Codex, Cursor, OpenCode, and every Agent Skills client.
Instructions file CodexOpenCode
Instructions for hannsxpeter/godaudits: This repository ships the godaudits Agent Skill and its deterministic runtime. It inspects an existing codebase end to end, records canonical state in .godaudits/AUDIT.json, and generates .godaudits/AUDIT.mdx plus optional SARIF with evidence-backed findings and an executable…
Plugin Claude Code
Audit a codebase end to end across 18 domains with a 437-check ledger, form-aware context, Pillars 1.1 routing, arc-ready drift detection, OWASP 2025 coverage, typed evidence, deterministic scoring, and an executable remediation plan.
Skill Claude CodeCodex
Audit a codebase end to end and emit validated JSON plus remediation MDX, or review one diff for non-obvious blast radius with explicit safety facts and a compiled merge proof gate. godaudits fingerprints the repository, detects six project forms, validates Pillars 1.1 and arc-ready artifacts, evaluates 437 checks…
Agent
This pillar covers fixture API contracts.
Agent
Agent "auth" from hannsxpeter/godaudits, covering scope, context, decisions, rules and workflows.
Agent
This pillar identifies the routing fixture.
Agent
Agent "data" from hannsxpeter/godaudits, covering scope, context, decisions, rules and workflows.
Agent
Agent "observe" from hannsxpeter/godaudits, covering scope, context, decisions, rules and workflows.
Agent
This pillar describes the fixture layout.
Agent
Agent "ui" from hannsxpeter/godaudits, covering scope, context, decisions, rules and workflows.
At most 3 mods per repository are shown here — the rest are on their repository pages: