black-hat
Critical analysis through mechanistic causal reasoning and proportionality testing. Challenges both over-complex and over-simple solutions.
$ npx -y skills add bjcoombs/ai-native-toolkit --agent claude-codeShips with ai-native-toolkit. Installing the plugin gets this agent.
How it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Critical analysis through mechanistic causal reasoning and proportionality testing. Challenges both over-complex and over-simple solutions.
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
Other agents on ai-native-toolkit.
- README
Subagent definitions invoked by the skills, or directly via `Task(subagent_type=...)`. Each file carries the frontmatter contract (`name`, `description`, `model`, `color`) documented in [`CLAUDE.md`](../CLAUDE.md). Back to the [Map of Content](../docs/index.md).
Open agent - 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 with evidence.
Open agent - blue-hat
Synthesizes perspectives from other thinking hats into coherent conclusions and actionable recommendations.
Open agent - green-hat
Creative problem-solving across the full complexity spectrum. Finds solutions nobody proposed.
Open agent - red-hat
Discovers who is affected and diagnoses what they feel. Actor discovery and emotional granularity as diagnostic tools.
Open agent - scribe
Creates clear, actionable documentation from synthesized analysis. Invisible framework.
Open agent