Claude Code mod
agent-trace
Reads the subagents, agent teams and Workflows the session launched from its transcript files and draws them in a docked panel as a flow diagram, agent details and file access
Install
/plugin marketplace add YeomYuJun/claude-mods
/plugin install agent-trace@claude-modsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: drives Claude, writes the clipboard, reads files, reads env vars, reads settings, reads the transcript, draws
- Sees
- every tool call
- Draws in
PanePromptHint- Hooks
session.startcommand.runui.closeui.renderui.scrolltool.call
From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.
How Claude Code mods work
- A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
- It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
- Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
- Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Details
- Repository
- YeomYuJun/claude-mods
- Folder
agent-trace- Marketplace
claude-mods- Author
- YeomYuJun
- License
- MIT
- Last updated
- 12 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is agent-trace?
Reads the subagents, agent teams and Workflows the session launched from its transcript files and draws them in a docked panel as a flow diagram, agent details and file access It is a mod for Claude Code, from YeomYuJun/claude-mods on GitHub.
What can the agent-trace mod access?
Its widest reach is "writes or runs" (drives Claude, writes the clipboard, reads files, reads env vars, reads settings, reads the transcript, draws). It sees every tool call. It draws in Pane, PromptHint. Like any mod, it runs with your permissions.
How do I install agent-trace?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add YeomYuJun/claude-mods and then /plugin install agent-trace@claude-mods.
More pane & dashboard mods
agent-todos
IrvingAguilar/claude-agent-todos
Live todo list of the tasks agents are running, with ODD feature tasks, in a side pane or a band above the prompt
agent-tree
Teodagher/teo-mods
Live board of your subagents: a little Claude critter per agent and one sentence on what it is doing
agent-theater
joydeep-pm/agent-theater
A pixel theater under the prompt: the little orange guy acts out what Claude is doing, with Haiku narration in a speech bubble.
agent-watch
hereshecodes/claude-mods
Flags risky Bash commands and writes to sensitive paths in a live sidebar pane, with a status-line tally.
agent-theater
afu-it/agent-theater
A pixel theater above the prompt: little orange Claude acts out each tool call at a desk while a monitor shows the command and Haiku narrates it.
agent-workshop
MarkMerk/markmerk-mods
A workshop where Claude and its subagents walk between tool stations: a pixel-art pane in the terminal, and a 3D window with a room for every session, to watch, prompt and answer them. English and German
Browse the most popular Claude Code mods, all pane & dashboard mods, or the skills and MCP server directories.