Audit Codebase — Security skill for Claude Code
Cold-start, time-boxed, multi-domain audit sweep — surfaces ranked findings with reasoning chains across security, performance, reliability, tooling, and testing.
How to install Audit Codebase
Installs to ~/.claude/skills/lugassawan-swe-workbench-audit-codebase/SKILL.md
mkdir -p ~/.claude/skills/lugassawan-swe-workbench-audit-codebase && curl -fsSL https://raw.githubusercontent.com/lugassawan/swe-workbench/HEAD/commands/audit-codebase.md -o ~/.claude/skills/lugassawan-swe-workbench-audit-codebase/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Codebase does
description: Cold-start, time-boxed, multi-domain audit sweep — surfaces ranked findings with reasoning chains across security, performance, reliability, tooling, and testing argument-hint: "[--time-box ] [--scope ] [--depth ] [--top-n ] [optional ticket ref]"
Cold-start audit of this codebase across multiple domains.
Step 1 — Parse arguments
From `$ARGUMENTS`, extract:
--time-box— default30m. Any trailingm/hsuffix
Alternatives in Security
- Migration Agent — Plans a token migration (format, tool, naming or tier): chains token-audit and naming-audit, builds the transf 194 ★
- Vuln Scan — Multi-agent security vulnerability sweep — fans out region-scoped hunters, verifies findings, and reports 107 ★
- Audit Ddd — DDD architecture audit with pattern recommendations 63 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Hatch3r Healthcheck
Open a QA and reliability epic surveying coverage gaps, flaky tests, and regression blind spots with one testi
Pentest Swarm AI
Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, a
Engineering Audit
Full-spectrum engineering health audit: scores Maintainability, Security, Testing, Architecture, Documentation
Finish Him
"Cold ass mother fcker." Sub-Zero. Audit the project, plan the path to win, then execute step by step with rea
Claude Warmline
Makes Claude Code's prompt-cache state visible: HOT/COLD in your statusline from Claude Code's own data, plus
Resilience Audit
Reliability / failure-mode audit — why distributed and async systems fall over: single points of failure, miss
Related Agents
Prototyper
The Prototyper builds rapid proof-of-concept implementations, throwaway spikes, and time-boxed experiments to
Wd Researcher
Use this agent for time-boxed investigations that feed specs - provider TOS and rate-limit realities, Claude C
Research Lead
Use for feasibility analysis, standards research, market/competitive scans, requirements discovery, library/fr