blueprint-research

# Blueprint Research

Handles the research phase of the blueprint workflow: Toolbox resolution, lessons discovery, local/external research decision, and spec review.

## Input

```yaml
feature_description: string
tech_stack: string | string[]  # From config-reader
discovery_result:
  user_familiarity: high | medium | low  # Do they know the codebase?
  user_intent: speed | thoroughness      # What matters more?
  topic_risk: high | medium | low        # Security, payments, external APIs?
  uncertainty_level: high | medium | low # Is the approach clear?
```

## 1. Resolve Toolbox + Discover Lessons

**Read config (parallel):**
```
/majestic:config tech_stack generic
/majestic:config lessons_path .agents-os/lessons/
```

**Spawn agents (parallel):**
```
Task(majestic-engineer:workflow:toolbox-resolver):
  prompt: "Stage: blueprint | Tech Stack: {tech_stack}"

Task(majestic-engineer:workflow:lessons-discoverer):
  prompt: "workflow_phase: planning | tech_stack: {tech_stack} | task: {feature_description}"
```

**Store outputs:**
- `research_hooks` → for Step 4 (external research)
- `coding_styles` → for Step 5 (skill injection)
- `lessons_context` → for architect agent

**Non-blocking errors:**
- No toolbox found → Continue with core agents
- Lessons directory missing → Continue
- Discovery returns 0 lessons → Log, continue
- Discovery fails → Log warning, continue

## 2. Local Research (Always Runs)

Fast, local research to understand codebase patterns before deciding on external research.

```
Task(majestic-engineer:research:git-researcher, prompt="{feature}")
Task(majestic-engineer:research:repo-analyst, prompt="{feature}")
```

**Store:** `local_findings` - patterns, conventions, similar implementations

## 3. Research Decision

Based on discovery signals + local findings, decide if external research adds value.

**Decision matrix:**

| Condition | External Research |
|-----------|-------------------|
| `topic_risk: high` (security, payments, external APIs) | **Alwa