prefrontalsys

ccplugins

Vault-aware output style: educational insights + automatic vault orchestration (finalize, memorize, recall, skill dispatch)

Execution specialist for mechanical tasks: bash ops, file management, GitHub operations, Ansible, repetitive changes. Haiku-tier for speed.

Essay and long-form prose editor. Identifies structural issues, AI writing tells, argument flow problems. Preserves authorial voice.

Software architect for implementation planning. Step-by-step plans, file mapping, architectural trade-offs. Use before coding multi-file tasks.

Expert prompt engineer. Takes any topic or request and produces a detailed, effective prompt for another LLM to execute.

Web and academic search specialist. Uses exa, Semantic Scholar, arxiv, DeepWiki, and Context7 for information retrieval.

Deductive debugging agent. Diagnoses bugs through systematic elimination, citing evidence for each ruled-out possibility until only the cause remains.

Deep reasoning agent for architectural decisions, multi-step hypothesis evaluation, and structured uncertainty analysis.

General-purpose Sonnet agent for coding, file ops, research, and moderate reasoning. The default when uncertain which agent to use.

Prose-first output style: longform writing, interlocutor mode, paragraph-first output, casual-authoritative voice (Ars Technica + Aeon).

Always-on thinking partner output style with Insight blocks and Notable blocks. Merges exploratory dialogue stance with educational code insights.