Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/timothywarner-org/context-engineering/warnerco-schematicanpx skills add timothywarner-org/context-engineering --skill warnerco-schematicagit clone --depth 1 https://github.com/timothywarner-org/context-engineeringWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00083 | $0.01406 |
| Opus 5 | $0.00042 | $0.00703 |
| Sonnet 5 | $0.00017 | $0.00281 |
| Haiku 4.5 | $0.00008 | $0.00141 |
Grade A, and why
warnerco-schematica scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WARNERCO Robotics Schematica
Agentic robot schematics system with semantic memory and retrieval-augmented generation.
Architecture
┌─────────────────────────────────────────────────────────────┐
│ FastAPI + FastMCP │
├─────────────────────────────────────────────────────────────┤
│ LangGraph Flow (9-node Hybrid RAG) │
│ parse_intent -> query_graph -> inject_scratchpad -> retrieve│
│ -> compress -> reason -> respond │
├─────────────────────────────────────────────────────────────┤
│ Hybrid Memory Layer │
│ +-------------------+ +-------------------+ +-----------+│
│ | Vector Store | | Graph Store | | Scratchpad|│
│ | JSON->Chroma-> | | SQLite + NetworkX | | In-memory |│
│ | Azure AI Search | | (Knowledge Graph) | | (Session) |│
│ +-------------------+ +-------------------+ +-----------+│
└─────────────────────────────────────────────────────────────┘
Project Structure
src/warnerco/backend/
├── app/
│ ├── main.py # FastAPI application
│ ├── config.py # Settings and environment
│ ├── models.py # Pydantic schemas
│ ├── routes.py # API endpoints
│ ├── mcp_tools.py # FastMCP tool definitions
│ ├── adapters/ # Memory backend implementations
│ │ ├── json_store.py
│ │ ├── chroma_store.py
│ │ ├── azure_search_store.py
│ │ ├── graph_store.py
│ │ └── scratchpad_store.py
│ └── langgraph/
│ └── flow.py # 9-node hybrid RAG orchestration
├── data/
│ ├── schematics/ # JSON source of truth
│ └── chroma/ # Vector embeddings
├── static/dash/ # SPA dashboards
└── .env # Configuration
Commands
cd src/warnerco/backend
# Local development
uv sync
uv run uvicorn app.main:app --reload --port 8000
# Index schematics into Chroma
uv run python -c "from app.adapters.chroma_store import ChromaMemoryStore; import asyncio; asyncio.run(ChromaMemoryStore().index_all())"
# MCP stdio server (for Claude Desktop)
uv run warnerco-mcp
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 157 lines · 83 tokens per session scan A f2d57b9b20ad
warnerco-schematica is a skill published in the GitHub repository timothywarner-org/context-engineering (27 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 1,406 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
remnic-entities
Browse entities in the Remnic knowledge graph and surface their facts and relationships. Trigger phrases include "tell me about the entity", "look up", "what do we know about".
query
Answer questions from the active raytsystem generation using local FTS5 retrieval, canonical record rehydration, verified source spans, and explicit gaps. Use for QUERY, knowledge lookup, comparison, relationship, temporal, or corpus questions; never answer factual gaps from model memory.
matryca-spatial-parser
Reuse Matryca graph primitives and the external spatial parser safely. Use for Markdown scanning, property injection, frontmatter, namespaces, fenced-code protection, AST extraction, or spatial RAG changes.
hybrid-memory
Hybrid memory strategy combining OpenClaw's built-in QMD vector memory with Graphiti temporal knowledge graph. Use for all memory recall requests.
ingest
Use when a raw source file needs to be ingested into the knowledge graph.