audit-flow skill

⚠️ MANDATORY ENTRY POINT — Execute Before ANY Other Action

Step 1: Read schema.sql

# ALWAYS read the schema first to understand tables, constraints, views
cat .claude/skills/audit-flow/schema.sql

Step 2: Check if DB exists — NEVER recreate

# Check for existing database
ls -la .audit/audit.db 2>/dev/null && echo "DB EXISTS - DO NOT RECREATE" || echo "No DB - safe to init"

Step 3: If DB exists, show current state

python .claude/skills/audit-flow/scripts/audit.py list

🚫 FORBIDDEN ACTIONS

Rule: If .audit/audit.db exists, ONLY use audit.py list, show, export, or INSERT operations. NEVER recreate.

Audit Flow

Interactive tracing of system flows with SQLite persistence. Supports multiple named flows per session, non-linear flows (branching/merging), and multi-format exports.

Organization Principles

Directory structure by purpose:

• Audits/Documentation/Compliance: docs/audits/{name}-{YYYY-MM-DD}/
• Ideation/Brainstorming: docs/ideation/{name}-{YYYY-MM-DD}.md (single file, no subdirectory unless artifacts needed)
• Debugging/Incident Review: docs/audits/{name}-{YYYY-MM-DD}/ (same as audits — captures evidence)
• Architecture Review: docs/audits/{name}-{YYYY-MM-DD}/ (same as audits — captures structural analysis)

Required files:

• INDEX.md (manifest, entry point)
• README.md (executive summary)
• {name}-audit.md (flow trace)

Lazy initialization: Create subdirectories only when artifacts exist

• screenshots/ network-traces/ diagrams/ code-samples/ test-results/ evidence/

Naming: {audit-name}-{type}.md

DB-First Discipline

Invariant: SQLite = sole source of truth. Context window: volatile, compacts without notice, hallucinates state.

🚨 CRITICAL: NEVER DESTROY EXISTING DATA

• If .audit/audit.db exists → it contains irreplaceable audit history
• NEVER run init when DB exists — use list to see what's there
• NEVER delete, drop, or recreate — only append

Constraints:

Checkpoint: Every 5 tuples → audit.py show

Interactive Workflow - ALWAYS ASK USER

1. Session Start - Ask:

Name: ___
Purpose: security-audit | documentation | compliance | ideation | brainstorming | debugging | architecture-review | incident-review
Description: ___ (optional)

Initialize directory immediately. Lazily create subdirectories when artifacts are generated.

2. Granularity - Ask:

[fine]   Function-level trace (~50-200 tuples)
         Use: Security audits, debugging

[coarse] Boundary-level trace (~10-30 tuples)
         Use: Documentation, high-level flows

Choose: fine / coarse

3. During Trace:

Ask at decision points: trace deeper? mark concern? add finding (severity)? note?

4. On Export:

Ask format: json | yaml | md | mermaid | all

Post-export: Generate INDEX.md manifest. Organize artifacts by type. Prune empty directories.

Quick Reference

Layers: CODE | API | NETWORK | AUTH | DATA

Relations: TRIGGERS | READS | WRITES | VALIDATES | TRANSFORMS | BRANCHES | MERGES

Semantic Rules for Relations

CRITICAL: BRANCHES Must Have Conditions. Every BRANCHES edge requires a condition describing which path. Example: BRANCHES [token expired] vs BRANCHES [token valid].

Observations vs Flow Steps

Flow steps = things the SYSTEM DOES (function calls, data reads, network requests). Verified by tracing code.

Observations = things the ANALYST NOTES (missing features, potential risks). Record as findings, not tuples.

Wrong pattern:

T50 "NO cross-tab sync"       ← observation, not a system action
T51 "React state NOT shared"  ← observation
T50 --VALIDATES--> T51         ← chaining observations as flow

Correct pattern:

-- Record as finding instead:
INSERT INTO findings (flow_id, session_id, severity, category, description)
VALUES (?, ?, 'medium', 'state-management',
        'No cross-tab sync: React state not shared across tabs');

Rule: NEVER chain observations with VALIDATES. If describing what the system DOESN'T do, use a finding.

Data Model

Session (audit container)
  └── Flow (named DAG with entry point)
       └── Tuple (node: layer + action + subject)
            └── Edge (relation + optional condition)

Storage & CLI

# Core
python .claude/skills/audit-flow/scripts/audit.py init              # Initialize DB
python .claude/skills/audit-flow/scripts/audit.py list              # List sessions
python .claude/skills/audit-flow/scripts/audit.py show <session>    # Show flows
python .claude/skills/audit-flow/scripts/audit.py show <session> <flow>  # Show flow details
python .claude/skills/audit-flow/scripts/audit.py export <session>  # Export all
python .claude/skills/audit-flow/scripts/audit.py export <session> -f <flow>  # Export one flow
python .claude/skills/audit-flow/scripts/audit.py validate <session>         # Validate flows

# Git integration
python .claude/skills/audit-flow/scripts/audit.py git-setup         # Configure merge/diff drivers (once)
python .claude/skills/audit-flow/scripts/audit.py db-merge %O %A %B # Git merge driver (auto-called)

# CSV backup/portability (optional)
python .claude/skills/audit-flow/scripts/audit.py csv-export               # DB → .audit/csv/*.csv
python .claude/skills/audit-flow/scripts/audit.py csv-import               # .audit/csv/*.csv → DB
python .claude/skills/audit-flow/scripts/audit.py csv-merge <theirs_dir>   # Merge two CSV sets

Non-Linear Flows

Branching: One tuple → multiple outgoing edges with conditions

INSERT INTO edges (from_tuple, to_tuple, relation, condition)
VALUES (5, 6, 'BRANCHES', 'token valid'),
       (5, 7, 'BRANCHES', 'token expired');

Merging: Multiple tuples → one tuple

INSERT INTO edges (from_tuple, to_tuple, relation)
VALUES (6, 8, 'TRIGGERS'),
       (9, 8, 'MERGES');  -- refresh path merges back

Files

• scripts/audit.py - CLI for all commands (init, list, show, export, validate, db-merge, git-setup, csv-\*)
• COMMANDS.md - Detailed SQL reference
• EXAMPLES.md - Full examples with non-linear flows
• schema.sql - Database schema
• .gitattributes - Git merge/diff driver config for audit.db