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 instructions/cunicopia-dev/knowledge-graph-rdbms/claude-mdgit clone --depth 1 https://github.com/cunicopia-dev/knowledge-graph-rdbmsWhat 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 | $0.03947 | $0.03947 |
| Opus 5 | $0.01973 | $0.01973 |
| Sonnet 5 | $0.00789 | $0.00789 |
| Haiku 4.5 | $0.00395 | $0.00395 |
Grade A, and why
knowledge-graph-rdbms CLAUDE.md 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 yesterday.
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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A label property graph (nodes, typed directed edges, labels, JSON properties) stored in SQLite. The core library has zero third-party dependencies — everything is stdlib + SQLite. Three front doors (Python library, kg CLI, MCP server) sit on one gated + logged engine, and a control plane (resolver.py + the backends/ package) lets all three address many named ontologies — each its own file (or, eventually, its own engine) — through one interface. See README.md for the full design narrative.
Commands
uv venv && uv pip install -e ".[dev]" # set up dev env (installs pytest + mcp)
pytest # run all tests (~62)
pytest tests/test_graph.py # one file
pytest tests/test_graph.py::test_name # one test
pytest -k events # by keyword
python bench/benchmark.py # perf, full p50–p99 distributions
python bench/charts.py # render assets/*.png from bench data (needs [charts])
python bench/runtimes/compare.py # CPython vs Node vs Bun SQLite comparison
kg stats # default ontology (~/.kgrdbms/graph.db)
kg schema # observed vocabulary: kinds, edge types, labels, keys-per-kind
kg schema --samples # + example ids and enum-like property values per kind
kg ontology list # the registry (the "db of dbs")
kg ontology create coffee --stance inferential # register a named ontology
kg --ontology coffee node add drink:latte --kind Drink # route to it (resolver)
kg fed schema # union vocabulary across ALL ontologies (multithreaded fan-out)
kg fed node person:ada # find an id across the federation (identity-aware)
kg link add coffee drink:latte ENJOYED_BY people person:ada # cross-ontology edge (backbone)
kg link same-as people person:ada wiki person:ada-lovelace # assert same real-world entity
kg prefix add person https://kg.local/person/ # CURIE prefix -> IRI (identity backbone)
kg --db /tmp/x.db node add a:1 --kind T # raw escape hatch: exact file, no registry
kg serve # run the MCP server (needs [mcp] extra)
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.
- yesterday First seen · 130 lines · 3,947 tokens per session scan A 32d0477a364f
knowledge-graph-rdbms CLAUDE.md is an instructions file published in the GitHub repository cunicopia-dev/knowledge-graph-rdbms (1 stars, last pushed 23d ago), licensed MIT. It adds 3,947 tokens to every session, about $0.0197 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.