codegraph CLAUDE.md

Repository instructions for codegraph, a project that gives a coding agent a map of a code repository. A repository is a project’s stored source code and related files.

In plain words
What is it for?
Use it when working on the codegraph project and needing its repository-specific guidance.
Why use it?
It helps the agent understand the project’s structure instead of working from disconnected search results. The provided excerpt points to additional instructions in an AGENTS.md file.

Instructions file

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/lzehrung/codegraph/claude-md
Clone the repo
git clone --depth 1 https://github.com/lzehrung/codegraph
Per session 21 This file is loaded in full into every session.
When invoked 21 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00021 $0.00021
Opus 5 $0.00010 $0.00010
Sonnet 5 $0.00004 $0.00004
Haiku 4.5 $0.00002 $0.00002

Measured 2d ago against content hash 631292fb8732, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codegraph 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 2d 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.

Origin

This is a copy

86% identical to kaneo CLAUDE.md — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 4 lines

What it actually says

CLAUDE

See AGENTS.md: AGENTS.md

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. 2d ago First seen · 4 lines · 21 tokens per session scan A 631292fb8732

Subscribe to this mod's changes

codegraph CLAUDE.md is an instructions file published in the GitHub repository lzehrung/codegraph (4 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to kaneo CLAUDE.md, differing in 6 lines, and is treated as a copy.