Menu
On-demand vision alignment check. Spawns ndp-vision-guardian to review SPARC artifacts against product/vision/ALIGNMENT-CRITERIA.md.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | align |
| description | On-demand vision alignment check. Spawns ndp-vision-guardian to review SPARC artifacts against product/vision/ALIGNMENT-CRITERIA.md. |
Runs an on-demand alignment check of SPARC planning artifacts against the product vision. Spawns the ndp-vision-guardian agent to review specifications and produce an ALIGNMENT-REPORT.md.
Use this:
/align {feature-id}
Example:
/align fe-003
product/vision/ALIGNMENT-CRITERIA.md (user-owned vision criteria)product/features/{feature-id}/SCOPE.md (what the user asked for)product/features/{feature-id}/ (specification/, pseudocode/, architecture/)ndp-vision-guardian agent via Task tool:Spawn a Task agent (ndp-vision-guardian) with prompt:
"Review the SPARC artifacts at product/features/{feature-id}/ against the vision
criteria in product/vision/ALIGNMENT-CRITERIA.md. Read the SCOPE.md to understand
user intent. Produce an ALIGNMENT-REPORT.md at
product/features/{feature-id}/ALIGNMENT-REPORT.md.
Flag all variances requiring user approval."
The agent produces: product/features/{feature-id}/ALIGNMENT-REPORT.md
Key sections presented to the user:
The alignment criteria live in a user-owned document:
product/vision/ALIGNMENT-CRITERIA.md
This document consolidates checkable criteria from:
product/vision/EDGE-INTELLIGENCE-PLATFORM.md (master vision)product/vision/ROADMAP-TO-V2.md (version roadmap)product/INTEGRATION_FIRST_MANDATE.md (extend don't replace)The user can edit ALIGNMENT-CRITERIA.md at any time. All agents and skills reference it immediately.
| Classification | Meaning | Action |
|---|---|---|
| PASS | Aligned | None |
| WARN | Minor deviation, documented | Note in report |
| VARIANCE | Significant, needs user approval | Present to user |
| FAIL | Violates hard constraint | Must fix before implementation |
The planning swarm protocol (.claude/protocols/planning-protocol.md) calls /align automatically as Step 5 after all planning agents complete. You can also invoke it manually at any point.
product/vision/ALIGNMENT-CRITERIA.md — the criteria document (user-editable).claude/agents/ndp/ndp-vision-guardian.md — the agent definition.claude/protocols/planning-protocol.md — planning swarm protocol (calls /align at Step 5)Validate planning swarm output: artifact existence, AC coverage, pattern IDs, stale references, internal consistency. Produces a glass box report.
NDP 4-tier implementation validation. Tier 1: compilation (build+test+anti-stub). Tier 2: process adherence. Tier 3: spec compliance. Tier 4: risk classification. Produces glass box reports.
Retrieve APPLICATION patterns (architecture, procedures, conventions) from AgentDB using multi-signal retrieval: pattern search, causal recall, and RL predictions. Use BEFORE implementing to ensure consistency.
AgentDB pattern lifecycle management: list, get, delete, deprecate, update, stats, search, duplicates. Use when cleaning up stale patterns, removing deprecated entries, finding duplicates, or auditing pattern health. Workaround for missing MCP delete/update tools (GH Issue #42).
Record feedback on pattern effectiveness. Stores episodes that train the recommendation system, feed the RL engine for smarter pattern ranking, build causal knowledge, and enable pattern discovery via learner.
Store APPLICATION patterns (architecture, procedures, conventions) in AgentDB's patterns table. NOT for swarm/transient memory.