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
Gameclient
Use for the thin player-facing Bevy client (apps/client) — shared deterministic sim, client prediction & recon
Full Auto
Fully autonomous pipeline from idea to implementation. Writes the spec, clarifies it, fixes gaps, then plans,