By ZivBA
Comprehensive toolkit for managing Basic Memory knowledge bases — slash commands for quick workflows, skills for note creation and quality enforcement, graph optimization, project organization, an autonomous memory-organizer agent, and automated validation hooks. For memory-related issues, advise the user to run /basic-memory-toolkit:doctor.
Capture a design or architectural decision with structured template
Resume previous work by loading context from Basic Memory
Start a development session with memory context loaded
Diagnose basic-memory-toolkit setup — checks prerequisite, MCP registration, tool availability, and stale config
Analyze knowledge graph health and suggest improvements
Audit project for quality issues in titles, metadata, observations, relations, and semantic markup
Find and fix broken, self-referential, or cross-project WikiLinks across all notes in a Basic Memory project. Use when the optimize-graph skill or /validate-project command identifies WikiLink issues at scale.
This skill should be used when reviewing a project for duplicate or overlapping notes, the user asks to "consolidate notes", "merge duplicate notes", "clean up overlapping content", or when the memory-organizer agent identifies consolidation candidates.
This skill should be used when creating a new note in Basic Memory, the user asks to "write a memory note", "create a note", "save this to memory", or when the memory-organizer agent needs to create notes with full rule enforcement.
This skill should be used when creating a new Basic Memory project, the user asks to 'create a new memory project', 'add a new project', 'set up a new project for X', or when the memory-organizer agent needs to establish a new project with proper index registration.
Runs pre-commands
Contains inline bash commands via ! syntax
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.
A comprehensive Claude Code plugin for managing Basic Memory knowledge bases with quality enforcement, structured workflows, automated validation, and schema-driven note types.
This plugin builds on the excellent work from the Basic Memory project by Basic Machines. It cherry-picks and extends patterns from their official repositories:
This toolkit adds development-focused features (two-tier validation, schema types for bugs/decisions/patterns, spec-driven development workflows) on top of their foundation.
/remember, /continue, /organize, /research, /dev-session, /capture-decision, /validate-project, /doctorThe plugin requires the basic-memory MCP server as an external prerequisite (no longer bundled — see docs/MIGRATION.md if upgrading from v2.x).
| Requirement | Purpose |
|---|---|
| uv | Runs the basic-memory MCP server via uvx |
basic-memory | The MCP server itself (auto-installed on first uvx invocation) |
| Claude Code CLI | Registers the MCP server with claude mcp add |
The setup script (Step 2 below) installs uv and registers the MCP server for you. See docs/INSTALL.md for full details, manual install steps, and MCP scope configuration.
Option A — From GitHub marketplace (recommended)
claude plugin marketplace add https://github.com/ZivBA/basic-memory-toolkit.git basic-memory-toolkit
Option B — Local plugin directory (development)
claude --plugin-dir /path/to/basic-memory-toolkit
Option C — Copy to project
cp -r basic-memory-toolkit /your/project/.claude-plugin/
If you installed from the CLI (Option A or B without launching Claude yet), run the setup script directly from the plugin directory before starting Claude Code:
# Linux / macOS / WSL / Git Bash
./scripts/setup-prerequisites.cmd
# Windows
scripts\setup-prerequisites.cmd
If you installed the plugin from inside an active Claude Code session, quit Claude Code first, then run the setup script. Do not use /reload-plugins — the script registers an MCP server via claude mcp add, which is best applied with no live session holding config state.
The script detects uv, installs it via the official Astral installer if missing, smoke-tests basic-memory, prompts for MCP registration scope, and registers the server. After it completes, start (or restart) Claude Code.
Inside Claude Code, run /basic-memory-toolkit:doctor for a full diagnostic report.
On first install, the plugin displays a welcome message with setup steps. On version updates from v2.x, it shows a migration notice (see docs/MIGRATION.md). On routine version bumps it shows a brief "updated" notice. On steady-state sessions (stored version matches plugin.json) the welcome/migration messages are silent — only the standard project-selection prompt fires.
Reconciliation state is stored in ${CLAUDE_PLUGIN_DATA}/version (typically ~/.claude/plugins/data/basic-memory-toolkit/version). To force the welcome/migration message to fire again, delete that file and restart Claude Code. The legacy v2.x flag at ~/.claude/basic-memory-toolkit.initialized is automatically cleaned up on first v3.0.0+ session.
npx claudepluginhub zivba/basic-memory-toolkit --plugin basic-memory-toolkitHarness-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
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.