ph3on1x

Use Muse Code from Claude Code to review code or delegate tasks.

3 skills · 8 commands · 1 agent · hooks

Use Antigravity from Claude Code to review code or delegate tasks.

3 skills · 7 commands · 1 agent · hooks

WISCI context engineering framework — Write, Isolate, Select, Compress, Iterate. Context store (.wisci/) whose notes quote their code evidence, checked on every load, per-stream handoffs (every compaction summary is one), session hooks, and commits with AI-Context trailers.

5 skills · hooks

Skill for orchestrating independent Claude Code sessions in cmux terminal — split panes, agent monitoring, browser automation, sidebar metadata, notifications, and full CLI coverage.

1 skill · hooks

GAN-inspired adversarial dev loop — Planner sequentially drives a Generator and Evaluator in fresh cmux panes, with a hard pass/fail gate per deliverable. Adapted from Anthropic's harness-design guidance for long-running agentic apps.

1 skill

Interview-style prompt refiner that picks a framework, fills gaps via AskUserQuestion, assembles a structured XML prompt, confirms, then executes it. In Claude Code, adds a refine prompt button above the prompt box.

1 skill

Recursive Language Model skill — programmatic codebase exploration via persistent Python REPL loop

1 skill

Claude Code subagents on the models you choose, local or cloud, called by name while your session stays on Claude.

Keeps personal data out of Claude: tool outputs are checked on your machine, and those with personal data go to a private model you choose through anymodel.