agentmods.dev

codexray CLAUDE.md

A set of instructions for using CodeXRay, a tool that maps code structure and relationships. It tells the coding agent which CodeXRay queries to use when exploring or changing a project.

In plain words
What is it for?
Use it to find symbols, trace callers and dependencies, assess change impact, inspect project structure, and identify complex, unused, or circular code.
Why use it?
It reduces the need to read many files manually and helps the agent understand how code parts connect before making changes.

Instructions file

7 6mo ago A scan 324 tokens original MIT
View the source file NeuralRays/codexray
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/neuralrays/codexray/claude-md
Clone the repo
git clone --depth 1 https://github.com/NeuralRays/codexray
Per session 324 This file is loaded in full into every session.
When invoked 324 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 $0.00324 $0.00324
Opus 5 $0.00162 $0.00162
Sonnet 5 $0.00065 $0.00065
Haiku 4.5 $0.00032 $0.00032

Measured 2d ago against content hash 473d0500d62e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexray 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.

CLAUDE.md · 25 lines

What it actually says

CodeXRay — AI Agent Instructions

This project uses CodeXRay for semantic code intelligence. Use these MCP tools instead of scanning files.

Workflow

  1. codexray_overview → project structure, languages, key symbols (START HERE)
  2. codexray_context → task-relevant code + snippets (replaces 5-10 file reads)
  3. codexray_search → find symbols by name/keyword (faster than grep/glob)
  4. codexray_semantic → find code by meaning ("authentication" → login, validateToken)
  5. codexray_node → detailed symbol info + full source code
  6. codexray_callers/callees → trace call relationships
  7. codexray_deps → full dependency tree of any symbol
  8. codexray_path → shortest connection between two symbols
  9. codexray_impact → blast radius analysis before changes
  10. codexray_hotspots → most critical/connected symbols
  11. codexray_deadcode → find unused functions/classes
  12. codexray_circular → detect circular dependencies
  13. codexray_complexity → find high-complexity functions
  14. codexray_files → browse file structure with stats
  15. codexray_status → index health check

Key Principle

Query the graph instead of scanning files. One codexray_context call replaces 5-10 file reads.

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 · 25 lines · 324 tokens per session scan A 473d0500d62e

Subscribe to this mod's changes

codexray CLAUDE.md is an instructions file published in the GitHub repository NeuralRays/codexray (7 stars, last pushed 6mo ago), licensed MIT. It adds 324 tokens to every session, about $0.0016 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.

Productivityai-codingastcall-graphclaude-codecode-analysiscode-intelligence
Related

Other instructions, from other repositories

codeweave-mcp CLAUDE.md

Instructions for semihkayan/codeweave-mcp, covering claude.md, what this project is, build & run, architecture and layers.

semihkayan/codeweave-mcp · 1,950 tokens

roam-code AGENTS.md

Instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).

Cranot/roam-code · 14,242 tokens

codeseek CLAUDE.md

Instructions for CodeBendKit/codeseek, covering claude.md, build & test, enter rust project directory, build and run tests.

CodeBendKit/codeseek · 1,559 tokens

jcodemunch-mcp CLAUDE.md

Claude Code instructions for jgravelle/jcodemunch-mcp, covering jcodemunch-mcp — project brief, current state, key files, cli subcommands and architecture notes.

jgravelle/jcodemunch-mcp · 34,089 tokens

bonsai-ninja AGENTS.md

Instructions for gromhacks/bonsai-ninja, covering bonsai-ninja, map a codebase, optional explicit semantic sidecar prewarm, explicit spelling for default syntax/construct indexing and optional during active editing.

gromhacks/bonsai-ninja · 5,841 tokens

jcodemunch-mcp AGENTS.md

AGENTS.md instructions for jgravelle/jcodemunch-mcp, covering code exploration policy, session-aware routing and model-driven tool tiering.

jgravelle/jcodemunch-mcp · 1,312 tokens