What is code-graph AGENTS.md?

A project guide for CodeGraph, a tool that analyzes a codebase and displays relationships between files, classes, and functions. It describes its Python backend, React interface, and FalkorDB graph storage.

Use it when working on repository analysis, code-relationship graphs, the web interface, database storage, or chat and navigation through the analyzed code.

It explains how code moves through the system, so an agent can find the right part to change and understand how analysis results reach the interface.

code-graph AGENTS.md — Instructions file by FalkorDB

Install

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.

agentmods

npx agentmods add instructions/falkordb/code-graph/agents-md

Clone the repo

git clone --depth 1 https://github.com/FalkorDB/code-graph

Made for: Codex, OpenCode.

Per session 1,894 This file is loaded in full into every session.

When invoked 1,894 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What 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	$0.01894	$0.01894
Opus 5	$0.00947	$0.00947
Sonnet 5	$0.00379	$0.00379
Haiku 4.5	$0.00189	$0.00189

Measured yesterday against content hash a8870e398732, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-graph AGENTS.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.

AGENTS.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeGraph - Agent Instructions

Knowledge graph visualization tool for codebases. Python FastAPI backend + React/TypeScript frontend + FalkorDB graph database.

Architecture

Backend (api/): FastAPI, async-first. All routes in api/index.py. Graph ops in api/graph.py. LLM chat via GraphRAG in api/llm.py.
Frontend (app/): React 18 + TypeScript + Vite. Tailwind CSS + Radix UI. 3D force-graph visualization (D3/Force-Graph).
Database: FalkorDB (graph DB on Redis). Metadata in Redis key-value store.
Analyzers (api/analyzers/): tree-sitter (Python), multilspy (Java, C#). Base class in analyzer.py, orchestrator in source_analyzer.py.

Data flow

User submits repo URL or folder path -> backend clones/reads and analyzes via language-specific analyzers
Entities stored in FalkorDB (nodes: File, Class, Function; edges: DEFINES, CALLS, etc.)
Metadata (URL, commit) stored in Redis
Frontend fetches graph, renders interactive visualization
User can chat (GraphRAG), explore neighbors, find paths

Directory structure

api/                  # Python backend
  cli.py              # cgraph CLI tool (typer)
  index.py            # FastAPI app, routes, auth, SPA serving
  graph.py            # FalkorDB graph operations (sync + async)
  llm.py              # GraphRAG + LiteLLM chat
  project.py          # Repo cloning and analysis pipeline
  info.py             # Redis metadata operations
  prompts.py          # LLM prompt templates
  auto_complete.py    # Prefix search
  analyzers/          # Language-specific code analyzers
  entities/           # Graph entity models
  git_utils/          # Git history graph construction
app/                  # React frontend (Vite)
  src/components/     # React components (ForceGraph, chat, code-graph, etc.)
  src/lib/            # Utilities
skills/code-graph/    # Claude Code skill for code graph indexing/querying
tests/                # Pytest backend tests
  endpoints/          # API endpoint integration tests
e2e/                  # Playwright E2E tests
  seed_test_data.py   # Test data seeder

Read the full file on GitHub · 181 lines

Changes

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 · 181 lines · 1,894 tokens per session scan A a8870e398732

Subscribe to this mod's changes

code-graph AGENTS.md is an instructions file published in the GitHub repository FalkorDB/code-graph (347 stars, last pushed 7d ago), licensed MIT. It adds 1,894 tokens to every session, about $0.0095 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.

Backend and APIs Databases Frontend LLM code-graph genai graph graph-database source-graph

code-graph AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CodeGraph - Agent Instructions

Architecture

Data flow

Directory structure

What this file has done since we first saw it

Other instructions, from other repositories

hugegraph AGENTS.md

tinkerpop AGENTS.md

kglite CLAUDE.md

pgGraph AGENTS.md

kivgraph AGENTS.md

EngramGraph AGENTS.md