By alexanderop
Persistent markdown memory for Claude Code. A brain/ vault your agent reads at session start and writes to when it learns. Six skills — reflect, ruminate, meditate (a learning loop) plus plan and review (principle-grounded work) and brain (read/write) — with hooks that inject the brain index at startup and re-index on writes. Plugin repackaging of brainmaxxing by Lauren Tan (https://github.com/poteto/brainmaxxing).
Read/write brain files (Obsidian vault at brain/). Use for any task that persists knowledge — reflection, planning, or direct edits. Triggers: brain/ modifications, "add to brain".
Scaffold the brain/ vault (folder + index.md) in the current project so the hooks and other brainmaxxing skills have somewhere to read and write. Use once when setting up brainmaxxing in a new project. Triggers: "init brain", "initBrain", "set up the brain", "create the brain vault".
Audit and evolve the brain vault — prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities. Triggers: "meditate", "audit the brain".
Break down medium-to-large tasks into phased plans in brain/plans/. Planning only — does not implement. Use for new features, multi-file refactors, or architectural changes — not small fixes. Triggers: "plan this", "break this down".
Reflect on the conversation and update the brain. Use when wrapping up, after mistakes or corrections, or when significant codebase knowledge was gained. Triggers: "reflect", "remember this".
Modifies files
Hook triggers on file write and edit operations
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.

Stupid simple persistent memory for Claude Code, packaged as a plugin. A markdown
vault (brain/) in your project that your agent reads at session start and writes
to when it learns something. It's also an Obsidian vault,
so you can browse your agent's memory yourself.
This is a plugin repackaging of poteto/brainmaxxing.
It ships the six skills and the two hooks — it does not seed the 16
starter principles. Your brain starts empty and grows from /reflect.
Four form a learning loop — reflect after sessions, ruminate over past
conversations, meditate to audit and prune. Two support structured work —
plan for phased plans, review for principle-grounded review. The brain
skill handles direct read/write of the vault.
/reflect — scan the conversation for things worth remembering and write
them to brain/. Most of your brain content comes from this./meditate — audit the vault against your skills, find contradictions,
prune stale notes, surface unstated principles./ruminate — mine past Claude Code conversations for patterns /reflect
missed. Good for bootstrapping from existing history./plan — break a medium-to-large task into phased plans in brain/plans/.
Planning only./review — principle-grounded review of code or plans. Review only./brain — read/write the vault directly./init-brain — scaffold the brain/ folder and index.md in a new
project. Optional — the vault is also created on demand by /reflect.Two hooks handle the plumbing, scoped to your project ($CLAUDE_PROJECT_DIR/brain/):
brain/index.md so the agent knows what knowledge
is available. No-ops until the vault exists.Write|Edit|MultiEdit) — rebuilds brain/index.md when files
under brain/ are added or removed. Bootstraps the index on the first write.The original repo also appended brain read/write rules to your CLAUDE.md. As a
plugin that's covered instead by the SessionStart hook (read-first) and the
brain skill (write/maintain), so there's nothing to merge into your project.
Add the marketplace and install:
/plugin marketplace add alexanderop/brainmaxxing-plugin
/plugin install brainmaxxing@brainmaxxing
Or run a working tree directly without installing:
claude --plugin-dir /path/to/brainmaxxing-plugin -p "<prompt>"
Optionally run /init-brain once to scaffold the brain/ folder up front.
Otherwise the vault is created on demand the first time /reflect (or /brain)
writes to it — no setup step required either way.
MIT. Original work by Lauren Tan (poteto/brainmaxxing). Plugin packaging maintained by Alexander Opalic.
npx claudepluginhub alexanderop/brainmaxxing-plugin --plugin brainmaxxingCreate skills, subagents, hooks, commands, and plugins for Claude Code
Modern Vue 3 development with TypeScript, Composition API, defineModel bindings, Testing Library for user-behavior tests, and MSW for API mocking
Vue language server for Claude Code
A help router plus an optional ship orchestrator for the AFK flow: prototype (throwaway logic/UI exploration) → grill (relentless plan interview, docs-aware) → implement (lead plans, workers run bounded TDD slices) → simplify (parallel cleanup) → qa (frontend/backend evidence verification). Ships a persistent brain/ memory vault (reflect, ruminate, meditate, plan, review, brain) that the flow reads before acting and writes back to as it learns.
Orchestrated multi-agent code review for Claude Code. A /review coordinator fans out to specialized reviewers (security, performance, code quality, docs) via concurrent `claude -p` subprocesses, then dedupes, judges severity, and emits one structured review. Inspired by Cloudflare's orchestrated AI review. Zero runtime dependencies.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
Memory compression system for Claude Code - persist context across sessions