agentic-layer-audit

# Agentic Layer Audit Skill

Evaluate a codebase's agentic layer maturity and identify investment opportunities.

## When to Use

- Assessing current agentic layer coverage
- Identifying gaps in automation
- Planning agentic layer investments
- Measuring progress toward 50%+ agentic time

## Core Concept

> "Am I working on the agentic layer or am I working on the application layer?"

This skill helps answer that question by auditing what exists.

## Audit Checklist

### 1. Commands Directory

Check for `.claude/commands/` or equivalent:

```markdown
Look for:
- chore.md      # Chore planning template
- bug.md        # Bug fix template
- feature.md    # Feature planning template
- implement.md  # Implementation HOP
- test.md       # Test execution template
- review.md     # Review template
```

### 2. Specs Directory

Check for `specs/` or equivalent:

```markdown
Look for:
- Issue-based specs (issue-*.md)
- Generated plans (chore-*.md, feature-*.md)
- Deep specs (complex multi-file architectures)
```

### 3. ADW Directory

Check for `adws/` or equivalent:

```markdown
Look for:
- adw_modules/agent.py  # Core agent execution
- Gateway scripts (adw_prompt.py, adw_slash_command.py)
- Composed workflows (adw_*_*.py)
- Triggers (trigger_*.py)
```

### 4. Hooks Directory

Check for `.claude/hooks/` or equivalent:

```markdown
Look for:
- pre_tool_use hooks
- post_tool_use hooks
- user_prompt_submit hooks
```

### 5. Agent Output Directory

Check for `agents/` or equivalent:

```markdown
Look for:
- ADW ID directories
- State files (adw_state.json)
- Output files (cc_*.jsonl, cc_*.json)
```

### 6. Worktree Support

Check for `trees/` or equivalent:

```markdown
Look for:
- Git worktree setup
- Isolation configuration
- Port allocation patterns
```

## Coverage Scoring

| Component | Points | Present? |
| --- | --- | --- |
| .claude/commands/ | 20 | |
| specs/ | 15 | |
| adws/ | 25 | |
| adw_modules/agent.py | 20 | |
| hooks/ | 10 | |
| agents/ | 5 | |
| trees/ | 5 | |

T