Audit

Audit

Project-wide health audit. Fans out to all analysis skills, evaluates findings, and writes .turbo/audit.md and .turbo/audit.html. Analysis-only — does not apply fixes.

Task Tracking

At the start, use TaskCreate to create a task for each phase:

1. Scope and partition
2. Threat model
3. Run analysis skills
4. Run /evaluate-findings skill
5. Generate markdown report
6. Generate HTML report

Step 1: Scope and Partition

If $ARGUMENTS specifies paths, use those directly (skip the question).

Otherwise, use AskUserQuestion to confirm scope:

• All source files — audit everything
• Specific paths — user provides directories or file patterns
• Critical paths — heuristically identify high-risk areas (entry points, auth, data handling, payment processing)

Once scope is determined:

1. Glob for source files in the selected scope. Exclude generated and vendored directories (node_modules/, dist/, build/, vendor/, __pycache__/, .build/, DerivedData/, target/, .tox/, and others appropriate to the project).
2. Partition files by top-level source directory. Cap at 10 partitions. If more than 10 top-level directories exist, group related directories or use AskUserQuestion to narrow scope. If a single directory contains 50+ files, sub-partition it by its immediate subdirectories.

Step 2: Threat Model

Check if .turbo/threat-model.md exists. If it does, continue to Step 3.

If missing, use AskUserQuestion to ask whether to create one before proceeding. The security review benefits from threat model context, but creating one adds time.

• Yes — launch an Agent tool call (model: "opus", do not set run_in_background) whose prompt instructs it to invoke the /create-threat-model skill via the Skill tool. Wait for completion before continuing.
• No — continue without a threat model.

Step 3: Launch All Analysis Agents

Use the Agent tool to launch all analysis agents below in a single assistant message so they run concurrently. Each Agent call uses model: "opus" and does not set run_in_background. Each Agent's prompt instructs the subagent to invoke its assigned skill via the Skill tool, with the partition's file list passed in for partitioned skills, and to treat the shared working tree and its git index as read-only — any empirical check runs in an isolated git worktree the agent discards afterward.

Expect (6 partitioned rows × number of partitions, plus 5 project-wide rows) Agent tool calls total. State the count explicitly when emitting the calls.

Partitioned Skills

For each skill below, launch one Agent per partition with the partition's file list in the prompt. Pass (skip peer review) annotations through to /review-code as an opt-out so it runs internal reviews only — /peer-review is scheduled as its own row to avoid duplicate peer-review runs.

| Skill | Scope | |---|---| | /review-code with correctness (skip peer review) | File list | | /review-code with security (skip peer review) | File list | | /review-code with api-usage (skip peer review) | File list | | /review-code with consistency (skip peer review) | File list | | /review-code with simplicity (skip peer review) | File list | | /peer-review | File list |

Project-Wide Skills

| Skill | Notes | |---|---| | /review-code with coverage (skip peer review) | Project-wide | | /review-dependencies | Project-wide | | /review-tooling | Project-wide | | /review-agentic-setup | Project-wide | | /find-dead-code | Has its own partitioning |

Step 4: Run /evaluate-findings Skill

Aggregate all findings from all agents. Run the /evaluate-findings skill once on the combined set.

Step 5: Generate Markdown Report

Write .turbo/audit.md using the template below. Populate the dashboard by counting findings per category and applying health thresholds. Output the dashboard as text before writing the file.

Report Template

# Audit Report

**Date:** 
**Scope:** 

## Dashboard

| Category | Health | Findings | Critical |
|---|---|---|---|
| Correctness |  |  |  |
| Security |  |  |  |
| API Usage |  |  |  |
| Consistency |  |  |  |
| Simplicity |  |  |  |
| Test Coverage |  |  |  |
| Dependencies |  |  |  |
| Tooling |  |  |  |
| Dead Code |  |  |  |
| Agentic Setup |  |  |  |
| Threat Model |  | — | — |

### Health Thresholds

- **Pass** — zero P0/P1 findings in this category
- **Warn** — P1 findings present but no P0
- **Fail** — P0 findings present

## Detailed Findings

### Correctness

### Security

### API Usage

### Consistency

### Simplicity

### Test Coverage

### Dependencies

### Tooling

### Dead Code

### Agentic Setup

### Threat Model

Step 6: Generate HTML Report

Convert the markdown report into a styled, interactive HTML page.

1. Run the /frontend-design skill to load design principles.
2. Read .turbo/audit.md for the full report content.
3. Write a self-contained .turbo/audit.html (single file, no external dependencies beyond Google Fonts) that presents all findings from the markdown report with:

• Dashboard health grid with severity color-coding (red=Fail, amber=Warn, green=Pass)
• Severity summary bar (P0/P1/P2/P3 counts)
• Sticky navigation between report sections
• Collapsible category sections
• Finding tables with file, line, and description columns
• Severity badges and color-coded group labels
• Entrance animations and hover states
• Print-friendly styles via @media print
• Responsive layout for mobile

Rules

• If any skill is unavailable or fails, proceed with findings from the remaining skills and note the failure in the report.
• /peer-review covers all concerns (correctness, security, api-usage, consistency, simplicity, coverage). Distribute its findings into their matching category sections. Deduplicate findings that overlap with the specialized reviewers.
• Does not modify source code, stage files, or commit.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: tobihagemann
• Source: tobihagemann/turbo
• License: MIT

Install and usage instructions live in the source repository linked above.