Audit Cycle — Security skill for Claude Code
Flow A — fully automated audit-firm lifecycle.
How to install Audit Cycle
Installs to ~/.claude/skills/solanabr-auditor-skill-audit-cycle/SKILL.md
mkdir -p ~/.claude/skills/solanabr-auditor-skill-audit-cycle && curl -fsSL https://raw.githubusercontent.com/solanabr/auditor-skill/HEAD/commands/audit-cycle.md -o ~/.claude/skills/solanabr-auditor-skill-audit-cycle/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Cycle does
name: auditor:audit-cycle description: Flow A — fully automated audit-firm lifecycle. Runs scope → context → tool-assisted first pass → domain-partitioned manual review → independent reconciliation → client report end-to-end, and delivers a professional audit report (MD + optional PDF). Audit-shaped automation, not a substitute for a human firm audit. argument-hint: "[path] [--scope full|program|backend|frontend]" allowed-tools: Read, Grep, Glob, Bash, Task
auditor-skill — Flow A: Aut
Alternatives in Security
- Trail Of Bits Claude-code-config — Opinionated production defaults from a top security firm: sandboxing, permissions, hooks, skills, MCP server c 1.6k ★
- Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★
- Beamer Skill — A Claude Code skill for creating, compiling, reviewing, and polishing academic Beamer LaTeX presentations 163 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Audit Assist
Flow B — AI-assisted iterative audit with a human in the loop. Same lifecycle as audit-cycle, but pauses at ch
Claude Code Dev Agents
A comprehensive collection of specialized Claude Code subagents for software development lifecycle. Domain-agn
Gws Meta Workflows
Six composable meta-workflows that chain Google Workspace CLI (gws) commands into end-to-end automations - inb
PayOps Agent Mesh
Governed agentic workflows for payments operations — reconciliation, audit prep, and financial analytics — bui
Talon
Penetration Testing MCP for Claude Code. AI-assisted security testing with automated recon, service enumeratio
LaptopAI Agent
Fully local, privacy-first autonomous AI agent for laptop management — LangGraph reasoning loop, Ollama local
Related Agents
Docs Knowledge
Team Historian. Reviews documentation completeness, ADR quality, knowledge persistence, and knowledge flow. Ca
Full Auto
Fully autonomous pipeline from idea to implementation. Writes the spec, clarifies it, fixes gaps, then plans,
Gameclient
Use for the thin player-facing Bevy client (apps/client) — shared deterministic sim, client prediction & recon