By chihebdk
Query the Agentic Transformation Navigator knowledge graph with Chiheb, your AI transformation consultant. Warm MCP server (kg_entity, kg_neighbors, kg_search, kg_by_type, kg_open_questions, kg_stale) plus a temporal-correct query skill. Self-contained: SQLite DB bundled, no sync required.
Chiheb is your AI transformation consultant. He synthesizes knowledge from the maturity model, playbook, and engagement methodology into clear, practical, insight-rich responses. Trigger when the user mentions "Chiheb", asks for consulting-style advice on AI transformation, wants a synthesized answer about dimensions/criteria/maturity, or needs actionable guidance on running an engagement. Chiheb never dumps raw data — he frames the insight, tells you what it means, and what to do about it.
Answer questions and generate insight from the the knowledge base (graph, ontology, semantic layer, knowledge base) with temporal correctness — current state only, dated and cited, so you never get a stalled answer. Use whenever the user asks a question about the engagement, org, people, deliverables, governance, funding, roles or operating model, or wants an insight / "what does the data say". By default answers use only status:current facts; superseded facts appear only when the user asks for history or "as of [date]". The read-side counterpart to ingest-document.
A curated collection of Claude Code plugins for the Agentic Transformation Navigator knowledge system.
| Plugin | Description | Install |
|---|---|---|
| agentic-nav-kg-she-chiheb | Knowledge graph query plugin with Chiheb, your AI transformation consultant. Self-contained SQLite DB, warm MCP server, temporal-correct queries. | See below |
Add the marketplace once, then install any plugin from it:
/plugin marketplace add chihebdk/agentic-nav-marketplace
/plugin install agentic-nav-kg-she-chiheb@agentic-nav-marketplace
This gives you automatic discovery, version tracking, and updates.
.plugin zipDownload the .plugin file from Releases and upload it to Cowork.
git clone https://github.com/chihebdk/agentic-nav-marketplace.git
Then point your Claude Code MCP config to the plugin's server:
{
"mcpServers": {
"agentic-nav-kg": {
"command": "python3",
"args": ["<path-to-repo>/plugins/agentic-nav-kg-she-chiheb/server/mcp_server.py"]
}
}
}
/plugin marketplace list # List registered marketplaces
/plugin marketplace update agentic-nav-marketplace # Refresh plugins
/plugin marketplace remove agentic-nav-marketplace # Unregister
Each plugin is self-contained — no external data sync, no raw source documents. Everything needed to query the knowledge graph is bundled:
.claude-plugin/ for Cowork compatibilityRaw source materials (playbook chapters, craft guides, engagement references, pipeline scripts, build tooling) live in the private authoring repo and are not distributed here. Only the compiled, query-ready artifacts ship.
161 nodes · 334 edges · 322 FTS passages:
Admin access level
Server config contains admin-level keywords
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.
npx claudepluginhub chihebdk/agentic-nav-marketplace --plugin agentic-nav-kg-she-chihebComposite plugin combining AgentLens assessment with deep Temporal SDK expertise. Generates production-grade Temporal workflows from agent code.
Give your AI a memory — mine projects and conversations into a searchable palace. 33 MCP tools, auto-save hooks, and guided setup.
MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.
Write SQL, explore datasets, and generate insights faster. Build visualizations and dashboards, and turn raw data into clear stories for stakeholders.
Agent Skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub
Excalidraw diagramming toolkit — auto-diagram any codebase, architecture diagrams, data flows, with PNG/SVG/URL export