By BartekCK
Session management — smart orchestrator that assesses work, recommends closing actions (session summary, sync AI docs, commit), and lets the user choose what to do
Audits and updates all AI/agent documentation files to ensure consistency and accuracy after implementation work. Covers agent definitions, skills, workflows, rules files, README, and AI-specific config files across multiple AI coding tools (Claude Code, Cursor, OpenCode, Antigravity, Gemini, GitHub Copilot). Triggers on 'sync AI docs', 'update agent files', 'check if docs are current', 'update rules files', 'ensure docs consistency', 'align AI instructions with code', or before finishing a development session. Also invoked by session-closer-agent as part of session-closing workflow.
Summarizes what changed during a session, writes a session document, and handles smart committing. Triggers on 'close session', 'save session', 'end of session', 'wrap up session', 'summarize session', 'what did we do', 'session summary'.
Provides the Conventional Commits format specification for git commit messages, including type definitions, formatting rules, and examples. Triggers on committing changes, writing commit messages, 'format my commit', 'how do I write a commit message', 'conventional commits', or 'what commit type should I use'. Also used by the session-closer-agent when committing session documentation.
Uses power tools
Uses Bash, Write, or Edit tools
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 marketplace of Claude Code plugins for development tooling, research, and session management.
The marketplace contains 9 plugins, all registered in the marketplace manifest. All plugins target the 8/10 quality threshold enforced by the brutal-critic plugin. The remaining technical debt is minor (db-connect DSN persistence workaround).
| Plugin | Description |
|---|---|
browser-manager | Browser automation via Chrome DevTools MCP |
my-serena | Semantic coding tools via MCP |
session-closer | Session closing — capture summaries, decisions, and sync docs |
code-researcher | Codebase research and pattern discovery |
database | Database inspection and querying via dbhub MCP |
docs-researcher | External documentation lookup |
brutal-critic | Uncompromising quality evaluator for code and text with PASS/FAIL reports |
software-development | Frontend/backend development agents with best-practice skills |
software-architect-nextjs | Next.js architect agent with MCP-powered docs and implementation delegation |
.claude-plugin/marketplace.json lists all available plugins with source pathsclose-session skill.claude-plugin/
marketplace.json # Plugin registry
plugins/
browser-manager/
brutal-critic/
code-researcher/
database/
docs-researcher/
my-serena/
session-closer/
software-development/
software-architect-nextjs/
README.md with usage detailsDatabase inspection and querying via dbhub MCP — explore schemas, run SQL queries, write migrations, and connect to databases
Browser automation and inspection via Chrome DevTools MCP — navigate, click, fill forms, inspect network traffic and console logs
Expert backend, frontend, and testing agents with TypeScript/Node.js specialization — SOLID principles, design patterns, React, Tailwind, strict typing, Vitest/Jest testing, and clean code practices
Codebase research and pattern discovery — investigate code patterns, locate references, find similar implementations, and provide placement guidance for new code
External documentation lookup — find and present official docs for libraries, packages, tools, and APIs from the internet
npx claudepluginhub bartekck/bartek-marketplace --plugin session-closerSave a structured session summary so you can pick up where you left off next time. Captures objectives, files changed, decisions, and generates a continuation prompt.
Session wrap-up workflow with multi-agent analysis pipeline for documentation, automation, learning, and follow-up suggestions
Session log archiver: saves conversations as Markdown or JSON for easy review
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).