agentic-layer-assessment

# Agentic Layer Assessment

Assess agentic layer maturity using the complete 12-grade classification system from TAC Lesson 14.

## When to Use

- Evaluating current agentic layer maturity
- Identifying the next grade to achieve
- Tracking progress toward Codebase Singularity
- Onboarding new team members to agentic patterns
- Planning agentic infrastructure investments

## Prerequisites

- Access to the codebase's `.claude/` directory
- Understanding of @adw-framework.md classification system

## The Classification System

Three classes with 12 total grades:

### Class 1: Foundation (In-Loop Agentic Coding)

| Grade | Component | Indicator |
| --- | --- | --- |
| 1 | Memory Files | CLAUDE.md exists with guidance |
| 2 | Sub-Agents | Task agents used for parallelization |
| 3 | Skills/MCPs | Custom skills or MCP integrations |
| 4 | Closed-Loops | Self-validating prompts |
| 5 | Templates | Bug/feature/chore classification |
| 6 | Prompt Chains | Multi-step composite workflows |
| 7 | Agent Experts | Expertise files with self-improve |

### Class 2: External Integration (Out-Loop Agentic Coding)

| Grade | Component | Indicator |
| --- | --- | --- |
| 1 | Webhooks | External triggers (PITER framework) |
| 2 | ADWs | AI Developer Workflows running |

### Class 3: Production Orchestration (Orchestrated Agentic Coding)

| Grade | Component | Indicator |
| --- | --- | --- |
| 1 | Orchestrator | Meta-agent managing fleet |
| 2 | Orchestrator Workflows | Human-orchestrator interaction |
| 3 | ADWs + Orchestrator | Full autonomous execution |

## Assessment Process

### Step 1: Scan Codebase

Check for indicators of each grade:

```bash
# Grade 1: Memory files
ls .claude/ CLAUDE.md

# Grade 2: Sub-agents
ls .claude/agents/

# Grade 3: Skills
ls .claude/skills/ || ls -d */skills/ 2>/dev/null

# Grade 4: Closed-loop patterns
grep -r "validation" .claude/commands/
grep -r "retry" .claude/commands/

# Grade 5: Templates
ls .claude/commands/ | grep -E "(chore|bug|feature)"

# G