codegenome-knowledge-graph

Rules for repositories analyzed by CodeGenome, a tool that maps code structure, dependencies, and symbols into a knowledge graph. They tell coding agents how to use that graph when investigating a codebase.

In plain words
What is it for?
Use it when exploring architecture, dependencies, symbols, or the effects of code changes in a repository with a .genome directory.
Why use it?
They help agents use the repository's architectural information instead of guessing from scattered files. They also define a fallback when the CodeGenome connection is unavailable and require refreshing the graph after changes.

Cursor rule for Cursor

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 rules/ogro-projukti/codegenome/codegenome-knowledge-graph
Clone the repo
git clone --depth 1 https://github.com/Ogro-Projukti/codegenome

Made for: Cursor.

Per session 550 This file is loaded in full into every session.
When invoked 550 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.

ModelPer sessionOnce invoked
Fable 5 $0.00550 $0.00550
Opus 5 $0.00275 $0.00275
Sonnet 5 $0.00110 $0.00110
Haiku 4.5 $0.00055 $0.00055

Measured yesterday against content hash 2c2acf9d4775, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codegenome-knowledge-graph 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/codegenome-knowledge-graph.mdc · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeGenome MCP Integration

You are operating within a repository analyzed by CodeGenome, an architectural knowledge graph tool. This project contains a .genome/ directory.

Core Directives

  1. Mandatory MCP Usage: When .genome/codegenome.db exists, you MUST use CodeGenome MCP access for all codebase, architecture, dependency, or symbol queries whenever it is available.
  2. Access Order: First use native CodeGenome MCP tools exposed in your context. If those tools are missing, you MAY try a local MCP HTTP endpoint such as http://127.0.0.1:7331/mcp when the user has started it or configured it. Treat this as MCP transport access, not as an arbitrary application HTTP API.
  3. Prefer Graph over Grep: Use graph-backed MCP tools instead of raw file searching (grep) or reading entire files blindly. The graph provides semantic understanding.
  4. Fallback Gracefully: If native MCP tools are missing and HTTP MCP access is unavailable, incompatible, or returns empty data, tell the user exactly what failed and what to configure. Then, if needed, read .genome/graph.json or .genome/exports/*.md before resorting to standard text searches.
  5. Keep Context Fresh: After modifying code files, remind the user to run codegenome analyze or start the live evolution server codegenome evolve --live to keep the graph updated.

Available MCP Capabilities

  • Discovery: search_nodes (find symbols)
  • Relationships: get_neighbors (imports, callers, callees)
  • Architecture: get_entry_points, get_dead_code, get_circular_deps, get_god_nodes
  • Metrics: get_complexity, get_churn, get_graph (summary statistics)
  • Evolution: get_timeline, get_changes (architectural diffs)

Constraints & Behaviors

  • Only read .genome/graph.json or .genome/exports/*.md directly if native MCP tools and local HTTP MCP transport are unavailable or fail to surface enough context.
  • Verify your MCP usage by monitoring tool call success. If native tools are missing, try the configured local HTTP MCP endpoint when possible. If both native and HTTP MCP access fail, politely ask the user to configure their editor's MCP settings to run codegenome mcp-start (stdio) or start the server with codegenome mcp-start --transport http.

Read the full file on GitHub · 30 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.

  1. yesterday First seen · 30 lines · 550 tokens per session scan A 2c2acf9d4775

Subscribe to this mod's changes

codegenome-knowledge-graph is a cursor rule published in the GitHub repository Ogro-Projukti/codegenome (23 stars, last pushed 1mo ago), licensed MIT. It adds 550 tokens to every session, about $0.0028 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.