audit-full

name	audit-full
license	MIT
compatibility	Claude Code 2.1.76+. Requires memory MCP server.
description	Single-pass codebase analysis leveraging Opus 4.6 1M context for comprehensive security scanning, architecture review, and dependency auditing. Loads entire codebases for cross-file pattern detection and generates structured audit reports with severity-ranked findings. Use when you need whole-project analysis before releases or security reviews.
argument-hint	[scope]
context	fork
version	1.2.0
author	OrchestKit
tags	["security","architecture","audit","dependencies","1m-context","cross-file"]
user-invocable	false
allowed-tools	["AskUserQuestion","Read","Grep","Glob","Bash","Task","TaskCreate","TaskUpdate","TaskList","PushNotification","mcp__memory__search_nodes"]
skills	["security-patterns","architecture-patterns","quality-gates"]
complexity	max
persuasion-type	discipline
effort	high
model	opus
metadata	{"category":"document-asset-creation","mcp-server":"memory"}

Full-Codebase Audit

Single-pass whole-project analysis leveraging Opus 4.6's extended context window. Loads entire codebases (~50K LOC) into context for cross-file vulnerability detection, architecture review, and dependency analysis.

Quick Start

/ork:audit-full                          # Full audit (all modes)
/ork:audit-full security                 # Security-focused audit
/ork:audit-full architecture             # Architecture review
/ork:audit-full dependencies             # Dependency audit

Opus 4.6 / 4.7: Uses complexity: max for extended thinking across entire codebases. 1M context (GA) enables cross-file reasoning that chunked approaches miss. On Opus 4.7, prefers xhigh effort for one additional cross-file pattern sweep.

1M Context Required: If CLAUDE_CODE_DISABLE_1M_CONTEXT is set, audit-full cannot perform full-codebase analysis. Check: echo $CLAUDE_CODE_DISABLE_1M_CONTEXT — if non-empty, either unset it (unset CLAUDE_CODE_DISABLE_1M_CONTEXT) or use /ork:verify for chunked analysis instead.

Effort (CC 2.1.111+): xhigh (Opus 4.7 only) adds a second pass that re-reads cross-module boundaries specifically looking for patterns the first pass normalized over. Silently falls back to high on other models; /ork:doctor warns on mismatch.

---

STEP 0: Verify User Intent with AskUserQuestion

BEFORE creating tasks, clarify audit scope using the interactive dialog.

Load: Read("${CLAUDE_SKILL_DIR}/references/audit-scope-dialog.md") for the full AskUserQuestion dialog with mode options (Full/Security/Architecture/Dependencies) and scope options (Entire codebase/Specific directory/Changed files).

---

CRITICAL: Task Management is MANDATORY

# 1. Create main task IMMEDIATELY
TaskCreate(
  subject="Full-codebase audit",
  description="Single-pass audit using extended context",
  activeForm="Running full-codebase audit"
)

# 2. Create subtasks for each phase
TaskCreate(subject=, activeForm=)  
TaskCreate(subject=, activeForm=)                    
TaskCreate(subject=, activeForm=)                          
TaskCreate(subject=, activeForm=)                        


TaskUpdate(taskId=, addBlockedBy=[])  
TaskUpdate(taskId=, addBlockedBy=[])  
TaskUpdate(taskId=, addBlockedBy=[])  


task = TaskGet(taskId=)  


TaskUpdate(taskId=, status=)  
TaskUpdate(taskId=, status=)