xref

A code cross-reference lookup that shows which functions call a chosen function and which functions it calls.

In plain words
What is it for?
Tracing callers and callees, checking multiple levels of function relationships, and finding cross-references for functions matching a pattern.
Why use it?
It gives a quick view of a function’s immediate connections without requiring a broader code audit.

Command

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 commands/marcosd4h/deepextractruntime/xref
Clone the repo
git clone --depth 1 https://github.com/marcosd4h/DeepExtractRuntime
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,174 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.01174
Opus 5 $0.00000 $0.00587
Sonnet 5 $0.00000 $0.00235
Haiku 4.5 $0.00000 $0.00117

Measured 2d ago against content hash 872200f8ce22, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xref 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.

commands/xref.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Reference Lookup

Overview

Quick cross-reference lookup for a function: show who calls it (inbound xrefs) and what it calls (outbound xrefs) in a compact table format. Lightweight alternative to /audit for when you just need to see a function's immediate neighborhood.

Usage:

  • /xref appinfo.dll AiLaunchProcess -- show callers and callees
  • /xref AiLaunchProcess -- auto-detect module
  • /xref appinfo.dll AiLaunchProcess --depth 2 -- show 2 levels of callers/callees
  • /xref appinfo.dll --search "Check*" -- xrefs for functions matching a pattern

IMPORTANT: Execution Model

This is an execute-immediately command. Do NOT present anything for user confirmation. Run and write the cross-reference results straight to the chat as your response. The user expects to see the completed output.

Execution Context

IMPORTANT: Any inline Python that imports helpers.* must run with cd <workspace>/.claude (so the .claude/ directory is on sys.path), not from the workspace root. Script invocations like python .claude/skills/.../script.py can be run from the workspace root because those scripts manage their own path setup.

Steps

Step 0: Preflight Validation

Validate arguments using helpers.command_validation.validate_command_args("xref", {"module": "<module>", "function": "<function>"}). If validation fails, report the errors and stop. On success, use result.resolved["db_path"] for subsequent script calls.

1. Locate the function

Tip: All skill scripts support --json for machine-readable output. Use --json when parsing script output programmatically.

Use the function-index skill for fast lookup:

python .claude/skills/function-index/scripts/lookup_function.py <function_name> --json

Or find the module DB first:

python .claude/skills/decompiled-code-extractor/scripts/find_module_db.py <module_name>

Once located, note function_id and db_path. Use --id <function_id> in all subsequent calls.

Read the full file on GitHub · 125 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. 2d ago First seen · 125 lines · 0 tokens per session scan A 872200f8ce22

Subscribe to this mod's changes

xref is a command published in the GitHub repository marcosd4h/DeepExtractRuntime (20 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,174 tokens. 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.