By zvoque
Give Claude a mindset that sticks: persistent personas that re-assert every turn. Run one, several in parallel, or convene them as a team that debates a topic — plus a guided persona creator. Command-controlled; never edits settings.json.
Create a new persistent persona for the personas plugin through a short guided interview, then a draft review. Use when the user wants to make, author, or define a new persona or mode, or runs `/personas new`.
Control surface for the personas plugin — activate a persona, switch solo/parallel, list, show status, create, delete, or convene a team debate. Use ONLY when the user runs the `/personas` slash command (e.g. `/personas contrarian`, `/personas list`, `/personas off`, `/personas team <topic>`). Do NOT activate from incidental mentions of "persona(s)" in conversation.
Convene the user's personas as a team of agents that debate a topic via native inter-agent messaging, then deliver a moderated synthesis. Use when the user runs `/personas team [topic]`, or asks to debate / stress-test / pressure-test / red-team / panel a decision, plan, or product with their personas.
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub zvoque/claude-personas --plugin personasGives the agent a persistent memory of architecturally-significant decisions. Detects stack, design-direction, and structural tradeoff decisions made by the user or the agent, records each as an ADR in a gitignored .adr/ folder, and injects the decision index into future sessions so settled decisions are never re-litigated or contradicted.
Tracks Claude Code skill usage over time, flags skills that have gone cold, and helps you reversibly prune unused personal skills. Configurable thresholds, keep/snooze suppression, and an interactive cleanup. Near-zero token cost, zero dependencies.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Unified status line for Claude Code with multi-CLI (Claude, Codex, Gemini, z.ai) usage monitoring, context, rate limits, and cost tracking
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses