UnleashedPPOS

AI Native Reframe — Security skill for Claude Code

Security community

Audit the current AI system design for human-team metaphor leakage and produce an engine/presentation/bridge split with parallelism-first defaults.

How to install AI Native Reframe

Installs to ~/.claude/skills/unleashedppos-unleashed-superpowers-ai-native-reframe/SKILL.md

Terminal

mkdir -p ~/.claude/skills/unleashedppos-unleashed-superpowers-ai-native-reframe && curl -fsSL https://raw.githubusercontent.com/UnleashedPPOS/unleashed-superpowers/HEAD/commands/ai-native-reframe.md -o ~/.claude/skills/unleashedppos-unleashed-superpowers-ai-native-reframe/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What AI Native Reframe does

description: Audit the current AI system design for human-team metaphor leakage and produce an engine/presentation/bridge split with parallelism-first defaults.

Audit the current AI-system design using the two-layer pattern. Run through four passes in order. Produce structured output.

Pass 0 — Human expertise check

List every role/agent in the current design. For each, answer:

What expertise did we mine about this role? What mistakes? What hard rules?
If anything is missing, fl

Alternatives in Security

Trail Of Bits Claude-code-config — Opinionated production defaults from a top security firm: sandboxing, permissions, hooks, skills, MCP server c 1.6k ★
OpenTag — Open-source, channel-native agent gateway for Slack 499 ★
Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★