Universal long-term project memory for AI coding agents — Claude Code, Cursor, Windsurf, Cline + 4 more. TDD rules, code graph, spec-driven dev, cross-session recall.
This repository also configures its own agents. See what skill-memory-bank tells them →
Agent Claude Code
Data / analytics / metrics specialist for memory-bank /mb work stages. SQL, dashboards, cohorts, ETL pipelines, instrumentation, A/B-test analysis. Does not own production application code.
Agent Claude Code
Android specialist for memory-bank /mb work stages. Jetpack Compose, Kotlin coroutines, Hilt/DI, Room, Material3. Falls back to mb-developer when stage is generic.
Agent Claude Code
Architecture / ADR / system-design specialist for memory-bank /mb work stages. Domain modelling, interface definition, ADR authoring, refactoring strategy. Does not ship features alone.
Agent Claude Code
Backend specialist for memory-bank /mb work stages. APIs, services, database, async/concurrency, server-side business logic. Falls back to mb-developer when stage is generic.
Agent Claude Code
Explores the codebase and writes structured Markdown documents into .memory-bank/codebase/. Invoked from /mb map with focus = stack|arch|quality|concerns|all. Output is integrated into /mb context.
Agent Claude Code
Generic memory-bank developer agent. Default implementer when no specialist role matches. Follows TDD discipline, Clean Architecture, and global RULES.md for the project.
Agent Claude Code
DevOps / infrastructure specialist for memory-bank /mb work stages. CI/CD, Docker, Kubernetes, Terraform, observability, release engineering. Falls back to mb-developer when stage is generic.
Agent Claude Code
Memory Bank diagnostician — finds and fixes internal inconsistencies across core files (roadmap.md ↔ checklist.md ↔ status.md ↔ backlog.md ↔ plans/). Invoked by /mb doctor. Uses deterministic mb-drift.sh first.
Agent Claude Code
This is a partial, not an agent. The installer places it above the text of every agent that lists it under compose:. It carries the discipline every MB implementer obeys; the role text that follows adds domain-specific rules and the output contract. When the two conflict, the stricter rule wins.
Agent Claude Code
Frontend specialist for memory-bank /mb work stages. React/Vue/Svelte/Solid components, browser UI, accessibility, responsive layouts, design-tokens-driven styling. Falls back to mb-developer when stage is generic.
Agent Claude Code
You are MB iOS, dispatched when the stage involves Apple-platform code: SwiftUI / UIKit views, view-models, navigation, persistence, networking, Apple-platform integrations (Sign in with Apple, Push, Widgets, App Intents, etc.).
Agent Claude Code
Independent final quality gate for Memory Bank governed workflows. Decides GO, GOWITHBACKLOG, or NOGO after verifier and lead-review reports.
Agent Claude Code
Memory Bank manager — maintains .memory-bank/ (context, search, note, tasks, actualize). Invoked by /mb context|search|note|tasks|update|done and PreCompact hook.
Agent Claude Code
QA / testing specialist for memory-bank /mb work stages. Test design, coverage strategy, edge-case enumeration, flake elimination, contract tests. Falls back to mb-developer when stage is generic.
Agent Claude Code
Read-only research over this codebase, project memory, library docs, GitHub prior art, and the open web. Routes each question to the Memory Bank code graph, semantic search, /mb recall, context7, gh, or web search, falls back to Grep/Read when an index is stale or absent, and returns conclusions cited to file:line or…
Agent Claude Code
Research specialist for Memory Bank workflows. Use for ecosystem research, implementation reconnaissance, source comparisons, technical due diligence, option matrices, and evidence-backed investigation before planning or implementation.
Agent Claude Code
Lead reviewer for Memory Bank governed review ensembles. Synthesizes aspect reviewer reports, verifies previous master report issues, deduplicates findings, and emits one canonical review report.
Agent Claude Code
Logic/spec-compliance reviewer for Memory Bank governed review ensembles. Focuses only on requirement coverage, behavior, runtime paths, edge cases, and regressions.
Agent Claude Code
Code-quality reviewer for Memory Bank governed review ensembles. Focuses on maintainability, SOLID/DRY/KISS/YAGNI, architecture boundaries, and implementation simplicity.
Agent Claude Code
Performance/scalability reviewer for Memory Bank governed review ensembles. Focuses on complexity, hot paths, memory, concurrency, IO, and operational cost.
Agent Claude Code
Security and risk reviewer for Memory Bank governed review ensembles. Focuses on secrets, protected paths, input/output boundaries, injection, authz/authn, filesystem/network risks, and data safety.
Agent Claude Code
Test-quality reviewer for Memory Bank governed review ensembles. Focuses on TDD evidence, regression coverage, test determinism, and whether tests assert real business/runtime facts.
Agent Claude Code
Code review agent for /mb work review-loop. Reads stage diff + pipeline.yaml reviewrubric and emits structured JSON verdict (APPROVED / CHANGESREQUESTED) with severity-classified issue list. Drives the severity-gate decision.
Agent Claude Code
Engineering-rules enforcer — runs deterministic SRP / Clean Architecture / TDD-delta checks against changed files and returns a structured JSON report. Invoked by /review, /commit, /pr, and plan-verifier Step 3.6.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: