By Hellblazer
Self-hosted three-tier knowledge management with plan-centric retrieval (nx_answer), specialized agents, semantic search, and RDR decision tracking for Claude Code.
Analyze codebase using codebase-deep-analyzer agent
Design architecture and create phased execution plans using architect-planner agent
Generates a handoff document under `/tmp/` that a future Claude Code session can read to pick up cold. Stores under `/tmp` (purged on reboot by macOS) so we don't accumulate stale handoffs in `~/.cache`. The chat response is one literal line: `cat <Target file>`. The user copies that line (mouse-select + cmd-C, or whatever their terminal supports), runs `/clear`, pastes, hits return. The new session reads the handoff and resumes.
Create implementation plan using strategic-planner agent
Debug test failures using debugger agent
This file documents the standard context exchange protocol used by all agents for consistent relays, context recovery, and knowledge management.
This file documents common error handling patterns for agents.
- **Context Protocol**: All agents reference `_shared/CONTEXT_PROTOCOL.md`
Executes development tasks using test-first methodology including feature implementation and refactoring. Use proactively for implementing features from specifications or executing architectural plans.
This directory contains shared resources used across multiple agents.
Use when synthesising across prose and code corpora or ranking candidates by a criterion — tries the analyze plan library first (search prose + code → reference-chain traversal → rank → generate), falls through to /conexus:query if nothing matches
Use when complex features need architectural design before implementation, or when system design decisions span multiple modules
Use when about to implement any feature, build any component, or make any behavioral change — requires design exploration and user approval before implementation
Use when working with catalog entries, resolving tumblers, creating links, understanding what's linked to a file, or seeding link context for the auto-linker. Covers resolve, link, context, and seed operations.
Use when controlling interactive CLI applications, debugging with pdb/gdb/jshell, spawning Claude Code instances, or working with REPLs and long-running processes
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power 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.
Uses Bash, Write, or Edit tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Persistent memory and semantic search for Claude. Three storage tiers that survive across sessions, an event-sourced document catalog with typed links, and a specification-before-code workflow for tracking decisions. Local-first; no API keys required. Knowledge compounds across conversations instead of evaporating when the window closes.
Start here: How I actually use Nexus — the conceptual overview and the shape of the substrate. Then Installing Nexus — a ten-minute hands-on walkthrough from uv tool install through your first search.
Python 3.12+, uv, git. For hybrid search, ripgrep. For the Claude Code plugin, Node.js (the bundled sequential-thinking and context7 servers spawn via npx).
Three surfaces share one host substrate: the nx CLI (the conexus package). Claude Desktop's .mcpb bundles it and resolves it on first launch; the Claude Code plugin and Cowork use a separately-installed CLI (uv tool install conexus). Pick the one that matches how you use Claude.
Download conexus.mcpb from the latest release and double-click. Claude Desktop registers it under Settings → Connectors. Requires uv installed on the host (the standard installer or Homebrew puts it where Claude Desktop resolves it — no PATH setup needed); deps resolve on first launch (~20s).
uv tool install conexus # 1. the nx CLI (the plugin's MCP servers ARE this package)
/plugin marketplace add Hellblazer/nexus # 2. add the marketplace
/plugin install conexus@nexus-plugins # 3. install the plugin
The plugin's MCP servers (nx-mcp, nx-mcp-catalog) are console-scripts from the conexus package, so the nx CLI must be installed too: /plugin install alone leaves the servers unable to launch. Install the CLI first (step 1; see CLI quick-start to then provision the storage backend).
The plugin ships 13 specialized agents, 45 skills (RDR lifecycle, plan-centric retrieval, dev workflows), and 48 MCP tools split across two focused servers. Session hooks load project context at startup.
Works automatically once the conexus plugin is installed in Claude Code on the host. State round-trips bidirectionally with the host CLI through the T2 daemon.
For the full deployment story across all three surfaces (install, daemon lifecycle, drift detection, uninstall), see docs/desktop-deployment.md.
npx claudepluginhub hellblazer/nexus --plugin conexusInjects Serena and Context7 MCP tool usage guidance into subagents via SubagentStart hook.
hal-9000 - Containerized Claude with MCP servers pre-installed
Locally-hosted Qwen 3.6 as a Claude Code coprocessor — delegate bulk or cheap work to long-lived supervised inference sessions over MCP. Backends include llama.cpp Metal on Apple Silicon and llama.cpp Vulkan on AMD Strix Halo.
Render a2ui v0.9 surfaces inline in Claude Code chat. Wraps payloads via palinex.wrap_as_mcp_ui_resource and returns them as MCP UI resources Claude Code renders as sandboxed iframes. Optional nexus integration substitutes chash references with chunk text at wrap time.
Hook-driven framework for recording deterministic Claude Code sessions (tutorials, demos, screencasts, fixtures). Drives an isolated child claude under tmux + asciinema + agg, coordinates via lifecycle-hook sentinels (no TUI scraping), validates the cast, renders a GIF.
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.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.