A command that follows a named symbol through a codebase's dependency graph and collects the related code within a token limit.

Use it with a symbol name, and optionally a project path or full graph traversal, to find its definition, callers, dependencies, and relevant source files.

It reduces the need to search through many files manually when you need to understand where a function, class, or other symbol is defined and used.

trace — Command for Claude Code by Barnett-Studios/cxpak

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add Barnett-Studios/cxpak

Claude Code

/plugin install cxpak

Made for: Claude Code.

Or install cxpak, the plugin that ships this one along with the rest of its 3 skills, 4 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/barnett-studios/cxpak/trace/github.svg)](https://agentmods.dev/commands/barnett-studios/cxpak/trace)

Your own site

<a href="https://agentmods.dev/commands/barnett-studios/cxpak/trace"><img src="https://agentmods.dev/badge/commands/barnett-studios/cxpak/trace/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/barnett-studios/cxpak/trace"><img src="https://agentmods.dev/badge/commands/barnett-studios/cxpak/trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 301 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.00301
Opus 5.5	$0.00007	$0.00120
Sonnet 5.5	$0.00003	$0.00060
Haiku 4.5	$0.00002	$0.00030

Measured 2mo ago against content hash 696aea6a6c7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

trace 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 2mo 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.

plugin/commands/trace.md · 32 lines

What it actually says

/cxpak:trace

Trace a symbol through the codebase dependency graph.

Steps

Parse arguments. The user must provide a symbol name (e.g., /cxpak:trace handle_request). If no symbol is provided, ask for one. The user may also provide a path (default .) and --all for full BFS traversal.
Ask for token budget. Ask: "Token budget for the trace? (default: 50k)" Use their answer or default to 50k.

Resolve cxpak binary:

CXPAK="$("${CLAUDE_PLUGIN_ROOT}/lib/ensure-cxpak")"

Run the trace:

"$CXPAK" trace --tokens <budget> --format markdown [--all] <symbol> <path>

Add --all only if the user requested full graph traversal.

Present the output. The trace contains:
- The target symbol and where it's defined
- Files that use/call the symbol (dependencies)
- Full source of relevant files, prioritized by dependency distance
Explain what was found. Summarize the symbol's role and how it connects to the rest of the codebase.

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.

2mo ago First seen · 32 lines · 17 tokens per session scan A 696aea6a6c7e

Subscribe to this mod's changes

trace is a command published in the GitHub repository Barnett-Studios/cxpak (32 stars, last pushed 13d ago), licensed Apache-2.0. It adds 17 tokens to every session and 301 once invoked, about $0.0001 per session on Opus 5.5. 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.

Debugging

trace next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
traceBarnett-Studios/cxpak	Command	32	13d ago	Apache-2.0	A	17	Claude Code
qa-changesOpenHands/extensions	Command	176	yesterday	MIT	A	63	Claude Code
react-nativegetsentry/toolkit	Command	957	yesterday	none	A	0	Claude Code
auditar-cascadingluanpdd/kit-mcp	Command	5	4d ago	MIT	A	54	Claude Code
http-serviceMadAppGang/magus	Command	14	yesterday	MIT	A	27	Claude Code
doctordoncheli/don-cheli-sdd	Command	59	2mo ago	Apache-2.0	A	76	Claude Code
doctorfatihkan/badi	Command	7	1mo ago	MIT	A	0	Claude Code