Always-on thinking partner output style with Insight blocks and Notable blocks
Custom Claude Code plugins by prefrontalsys.
| Plugin | Description |
|---|---|
holden | Holden personality system — soul, constitution, hooks, agents |
thinking-partner | Always-on thinking partner output style with Insight and Notable blocks |
vault-aware-style | Vault-aware output style with automatic vault orchestration |
prose-style | Prose-first output style for longform writing |
/plugin install holden@ccplugins
/plugin install thinking-partner@ccplugins
Agent definitions (doer, editor, engineer, planner, prompter, searcher, sherlock, skiller, thinker, worker, writer, knowledge-guide) are provided by the holden plugin. Individual agent plugins have been removed.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimProse-first output style — longform writing, interlocutor mode, paragraph-first output
Vault-aware output style: educational insights + automatic vault orchestration (finalize, memorize, recall, skill dispatch)
Deductive debugging agent. Diagnoses bugs through systematic elimination, citing evidence for each ruled-out possibility until only the cause remains.
Execution specialist for mechanical tasks: bash ops, file management, GitHub operations, Ansible, repetitive changes. Haiku-tier for speed.
Multi-agent orchestration system for Claude Code
npx claudepluginhub prefrontalsys/ccplugins --plugin thinking-partnerStructured thinking and multi-perspective deliberation tools
A deterministic thinking partner that challenges assumptions and applies 150+ mental models to sharpen decisions, solve problems, and think more clearly. Features orientation detection, cognitive operations framework, and structured diagnostic workflows.
Proactive enhancement layer for AI agents — learns user patterns from any memory store, upgrades prompts into full intent, takes engineer-grade initiative that advances the goal instead of generic filler, predicts the next request, verifies everything before delivery, scans for AI slop, orchestrates subagents when available, onboards itself to any host on first run, and runs a self-improvement loop that sharpens its own heuristics. Universal adapter runs on Claude Code, Codex, Hermes, OpenClaw, opencode, Cursor, Gemini CLI, and custom loops.
Compile humans into AI agents through deep interviews. Conducts comprehensive behavioral interviews, analyzes work artifacts via MCP tools, and generates installable Claude Code plugins that embody a person's decision-making, communication style, and expertise.
Portable prompt bundle that turns any LLM into a patient interviewer who asks the right questions. For generalist knowledge workers.
Ultra-compressed communication mode. Cuts 65% of output tokens (measured) while keeping full technical accuracy by speaking like a caveman.