Claude Code mod
agent-radar
Live pane of running agents: Claude subagents and the Codex runs they launch, with model, effort, tokens, context, thinking, time and launch method
Install
/plugin marketplace add cioxideru/agent-radar
/plugin install agent-radar@agent-radarMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: runs processes, drives Claude, writes the clipboard, reads files, reads env vars, reads mod state, persists state, draws
- Sees
- subagent spawns, Bash calls, Monitor calls
- Draws in
Pane- Hooks
session.startsession.attachcommand.runui.closeagent.spawnturn.startturn.completeturn.steptool.callsession.appendui.render
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
- cioxideru/agent-radar
- Folder
.- Marketplace
agent-radar- Author
- cioxideru
- License
- Apache-2.0
- Last updated
- 12 November 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is agent-radar?
Live pane of running agents: Claude subagents and the Codex runs they launch, with model, effort, tokens, context, thinking, time and launch method It is a mod for Claude Code, from cioxideru/agent-radar on GitHub.
What can the agent-radar mod access?
Its widest reach is "writes or runs" (runs processes, drives Claude, writes the clipboard, reads files, reads env vars, reads mod state, persists state, draws). It sees subagent spawns, Bash calls, Monitor calls. It draws in Pane. Like any mod, it runs with your permissions.
How do I install agent-radar?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add cioxideru/agent-radar and then /plugin install agent-radar@agent-radar.
Is agent-radar popular?
cioxideru/agent-radar has 1 GitHub stars and 0 forks, and is included in 1 curated Claude Code list. It was last updated on 12 November 2026.
More context & usage mods
agent-flow
1diegorv/claude-mods-diegorv
A live tree of the session's subagents and teammates in a pane: status, current tool, time, calls and tokens
agent-radar
1fbrogno/claude-mods
Alle Claude-Code-Sitzungen und Subagents auf einen Blick, Kaltstart-Wächter gegen teure Cache-Neuaufbauten, Keepwarm (Cache in der Pause per Mini-Ping warm halten), Modellwahl-Pflicht für Subagents, Such-Agents auf Haiku.
agent-crew
1jduerrmann/agent-crew
One pane for every subagent (tabs, details, timeline), the files they read, changed and committed (history, diffs, conflicts), and the session's usage.
agent-threads
1angomedia/claude-mods
A side pane showing the main thread and every subagent: model, cost and a progress bar for each, with the overall progress on top
afk-timer
1tlq5l/afk-timer
Shows how long you have been away from a Claude Code session and warns when its prompt cache has likely expired, so you can /clear instead of paying to re-read a big conversation
agent-tree
1russellpope/claude-mods
Pane of the herdr agents this session spawned, and theirs: status, model, context, cost, ticket. /agent-tree toggles it; a global view lists every herdr agent.
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.