codegraph

A set of rules for using a local semantic code graph to answer structural questions about a codebase. The graph connects functions, symbols, files, callers, and dependencies.

In plain words
What is it for?
Use it to find callers, assess change impact, prepare file-editing context, search symbols, summarize modules, review pull requests, and investigate bugs.
Why use it?
It reduces the need to search files manually when you need to understand how code is connected or what a change might affect.

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/codegraph-ai/codegraph-rules-for-agents/codegraph
Clone the repo
git clone --depth 1 https://github.com/codegraph-ai/codegraph-rules-for-agents

Made for: Cursor.

Per session 617 This file is loaded in full into every session.
When invoked 617 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 $0.00617 $0.00617
Opus 5 $0.00309 $0.00309
Sonnet 5 $0.00123 $0.00123
Haiku 4.5 $0.00062 $0.00062

Measured yesterday against content hash f5caca4ebcca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codegraph 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.

.cursor/rules/codegraph.mdc · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeGraph — local code intelligence

Persistent semantic graph of your codebase. Resolves references — "who calls X?" is a single tool call, not multi-file grep.

First time? Run codegraph_reindex_workspace once (5-30s). Index persists across sessions.

Top 5 tools (use these first)

When you need Call this NOT this
Who calls function X? codegraph_get_callers grep for the function name
What breaks if I change X? codegraph_analyze_impact reading every importing file
Context for editing a file codegraph_get_edit_context reading 5+ files manually
Find a symbol by name codegraph_symbol_search grep -r across the project
Module structure overview codegraph_get_module_summary ls + reading each file

URI format: file:///absolute/path. Use paths from symbol_search results directly. Compact mode: pass compact: true for shorter output when scanning.

Common workflows

  • PR review: pr_context — one call: blast radius, test gaps, stale docs, reviewers
  • Refactoring: symbol_searchanalyze_impactget_edit_context
  • Bug triage: search_by_errorget_callersget_ai_context(intent: "debug")
  • Onboarding: get_module_summaryfind_entry_pointsget_call_graph

Decision rule

  1. Structural question? (callers, deps, impact) → codegraph tools
  2. Text question? (exact string, regex) → grep/read
  3. Not sure? → Try codegraph_symbol_search first. Empty → run codegraph_reindex_workspace.

More tools

Navigation: get_callees, get_call_graph, get_dependency_graph, traverse_graph, find_by_imports, find_entry_points Quality: analyze_complexity, find_hot_paths, find_circular_deps, find_dead_imports PR review: pr_context (blast radius, test gaps, stale docs, commit hint, reviewers) Docs: index_markdown, search_docs, verify_design, design_gaps, generate_architecture_doc Memory: memory_store (pass agentSource: "cursor"), memory_search, memory_context

Read the full file on GitHub · 50 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 · 50 lines · 617 tokens per session scan A f5caca4ebcca

Subscribe to this mod's changes

codegraph is a cursor rule published in the GitHub repository codegraph-ai/codegraph-rules-for-agents (4 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 617 tokens to every session, about $0.0031 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.