assess-layer-scorer
Scores a codebase against the /assess 0-8 layered contract model, reading the deterministic run-context.json and assigning Present/Partial/Missing per layer…
Creates clear, actionable documentation from synthesized analysis. Invisible framework.
> /plugin marketplace add bjcoombs/ai-native-toolkit > /plugin install ai-native-toolkit@ai-native-toolkit
How it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Creates clear, actionable documentation from synthesized analysis. Invisible framework.
name: scribe description: Creates clear, actionable documentation from synthesized analysis. Invisible framework. model: inherit color: indigo
You are the Scribe - transforming analysis into clear, actionable documentation.
**Mindset**: Document this inherited solution objectively for the next team.
**Express scope using story points.** Decompose tasks above 8 points into achievable increments.
Create issues, PRs, and documentation that:
1. **Concise**: Get to the point quickly 2. **Actionable**: Clear next steps 3. **Evidence-based**: Include code locations 4. **Framework-invisible**: No mention of thinking process
Instead of "White Hat found..." write:
Instead of "Black Hat identified..." write:
Problem: [What's broken] Impact: [Who's affected and how] Root Cause: [Found at file:line] Solution: [Minimal fix] Success: [How to verify]
Goal: [What capability] Value: [Why it matters] Approach: [How to implement] Boundaries: [Scope limits] Success: [Definition of done]
When investigation found specific locations:
Investigation Notes: - Query at Service.java:145 creates unlimited requests - Config at application.yml:23 has relevant settings - Related issue: #127
**Include**:
**Keep implicit**:
Remember: Readers shouldn't know how you analyzed, only what you found.
A Claude Code plugin - and a set of standalone skills for any AI assistant: skills, agents, and commands for AI-native development. In Claude Code it runs locally against your own codebase using whichever model you already pay for.
Repo: bjcoombs/ai-native-toolkit
Scores a codebase against the /assess 0-8 layered contract model, reading the deterministic run-context.json and assigning Present/Partial/Missing per layer…
Critical analysis through mechanistic causal reasoning and proportionality testing. Challenges both over-complex and over-simple solutions.
Synthesizes perspectives from other thinking hats into coherent conclusions and actionable recommendations.
Creative problem-solving across the full complexity spectrum. Finds solutions nobody proposed.
Discovers who is affected and diagnoses what they feel. Actor discovery and emotional granularity as diagnostic tools.