Architect Audit — Security skill for Claude Code
Audit brownfield codebases and acceptance test evidence against SRS/ADR specifications (UC-04).
How to install Architect Audit
Installs to ~/.claude/skills/ldqanh1408-architect-agent-framework-architect-audit/SKILL.md
mkdir -p ~/.claude/skills/ldqanh1408-architect-agent-framework-architect-audit && curl -fsSL https://raw.githubusercontent.com/ldqanh1408/architect-agent-framework/HEAD/commands/architect-audit.md -o ~/.claude/skills/ldqanh1408-architect-agent-framework-architect-audit/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Architect Audit does
description: Audit brownfield codebases and acceptance test evidence against SRS/ADR specifications (UC-04) argument-hint: "[thư mục dự án (tùy chọn — tự động quét code, test và SRS)]"
`/architect-audit` — Brownfield Codebase & Acceptance Evidence Auditor (`UC-04`)
Perform an exhaustive architectural drift and acceptance gate audit across implementation repositories and test suites in **$ARGUMENTS** against upstream SRS/ADR authority.
1. Mandatory Reference Loading
Before auditi
Alternatives in Security
- Skill Audit — Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review 2.8k ★
- Agentseal — Security toolkit for AI agents 344 ★
- CodexQB — CodexQB is a Codex plugin for evidence-backed repo comprehension, planning, QA audit, and gated implementation 186 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Full Feature
End-to-end feature pipeline from ADR to deploy-ready PR. Chains architect-planner → implementation agents → te
Security Claude
A Claude Code skill for security architecture intelligence — analyzes codebases for security design flaws, thr
Spec Check
Audit GWT acceptance test specs for implementation leakage. Optionally provide a specific file path.
Genlayer Agent Playbook
Agent-ready GenLayer builder playbook: confirmed GenVM nondet bug catalog, contract skeletons, direct-mode tes
Codebase Tribunal
⚖️ Your codebase is on trial: 5-8 AI expert personas (PM/architect/backend/security/QA/DevOps) audit any proje
QA Lab
Two-agent QA and application security assessment workspace. Two AI coding agents from two providers run indepe
Related Agents
N2i Sec Category Auditor
Audits one category of the n2i-sec-audit checklist (A, B, C, or D) against the code, read-only, and returns a
Onboard Agent
You are an onboarding agent that analyzes existing codebases and creates initial continuity ledgers. You help
Squad QA
Operate as the squad's behavioral QA gate — verify observable behavior against acceptance criteria and risk, r