Claude Code mod
agent-watch
A progress bar above the prompt and a live agents panel for any subagents Claude starts, with model, context, cost and time. Fork of johnnyvizz's savvy-progress (MIT).
Install
/plugin marketplace add Barncore/agent-watch
/plugin install agent-watch@agent-watchMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: drives Claude, reads env vars, reads settings, reads mod state, draws
- Sees
- mcp__agent-watch__progress calls, mcp__agent-watch__step calls, Agent calls, subagent spawns, every prompt
- Draws in
PaneAbovePrompt- Hooks
session.startcommand.runtool.callagent.spawnturn.stepturn.completeprompt.submitui.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
- Barncore/agent-watch
- Folder
.- Marketplace
agent-watch- Author
- Barncore
- License
- MIT
- Last updated
- 13 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is agent-watch?
A progress bar above the prompt and a live agents panel for any subagents Claude starts, with model, context, cost and time. Fork of johnnyvizz's savvy-progress (MIT). It is a mod for Claude Code, from Barncore/agent-watch on GitHub.
What can the agent-watch mod access?
Its widest reach is "writes or runs" (drives Claude, reads env vars, reads settings, reads mod state, draws). It sees mcp__agent-watch__progress calls, mcp__agent-watch__step calls, Agent calls, subagent spawns, every prompt. It draws in Pane, AbovePrompt. Like any mod, it runs with your permissions.
How do I install agent-watch?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add Barncore/agent-watch and then /plugin install agent-watch@agent-watch.
More context & usage mods
agent-tree
TheClaessens/thomas-claude-mods
Live graph of this session's agent, its subagents and theirs: model, context, tokens, status and assignment.
agent-watch
estruyf/claude-agent-watch-mod
Keeps the number of running Claude Code sessions under a limit and shows the ones waiting on you or sitting idle.
agent-tree
russellpope/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.
ai-link
Creeperprol/claude-mods
Side panes for Claude Code: a usage pane (context, limits, cost, tools) and session link (sessions message each other, host mode)
agent-router
CiroVilmer/jev-agent-router
Picks the model and effort of every subagent from its task type; with hot mode on, raises them when the 5-hour window resets with usage to spare
anime-cheer
a252937166/cc-mod
Voiced pixel anime girls who roam the Claude Code transcript: they dance while Claude works and serve tea when it is done, and they do chores too: usage reports, a guard on dangerous commands, secret scans, quick code reviews and task recaps (/waifu help)
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.