ClaudeCodeMod

All shelves / Mods / Workflow

agent-watch

By ice-lfernandes

agent-watch is a Claude Code workflow mod by ice-lfernandes.

Draws each subagent's tokens and a stall toast, and the last tool calls, with a summary of the heaviest agent when they finish.

Draws

Install

The marketplace name is lfernandes-mods.

In Claude Code
/plugin install agent-watch --marketplace ice-lfernandes/claude-code-mods
Open the repo

It runs inside the Claude Code process. The side panel is only what the author's README names. Read the repo before you install, or run claude plugin validate on the plugin folder.

Version
0.3.1
License
MIT
Repo stars
7
Last change
2026-10-09

What it can reach

  • Draws in the session
  • Reads usage or context figures
  • Sees tool calls

The repository README says these mods require Claude Code 2.1.287 or later. While subagents run, a status line shows how many are running, their tokens, and a stall mark, and it clears when they finish. Tokens come from each model request: input that was not cached, cache read, cache written, and output. The lead row is the main conversation. Tokens from loops that are not agents show as other loops. A running agent with no model request and no tool call for 5 minutes, by default, gets one toast that says what it is stuck on: thinking, a tool call, or nothing. The alert re-arms when the agent does something again. Teammates between turns, and agents held on their own background work, never count as stalled. When the last active agent ends, a toast names the agents, the tokens, the wall time, and the heaviest agent with its share. On a subscription it also says how much of the 5-hour window that wave used. /watch opens the pane. Press an agent's name and the row shows its last 5 tool calls. A stalled agent's investigate button puts a request about it in the prompt. The README says nothing stops the agent. /watch demo adds three fake agents. Language defaults to auto: Portuguese when the system language is Portuguese, English otherwise. From a clone, one session is claude --plugin-dir ./agent-watch. The README says reading each response's usage adds a small cost to each request, the main conversation included. Its reach table marks network, processes, files, model calls, and sending data anywhere as no.

The install name is agent-watch. This page adds the author's name. The install line has no @suffix. The marketplace name is lfernandes-mods. The marketplace also holds limits-meter, allowlist-coach, test-hud, launchpad, and plain-view. The status line and the pane of the subagents are why this page files it under workflow. agent-radar draws one line per running subagent, with the time and the tool count. review-watch draws one line per running code review. This one is the tokens, the stall, and the last tool calls. investigate fills the prompt. Demo agents are fake.

Demo

A rendered sample of the watch pane, with demo agents, a stall, the status line, and toasts for a finished wave and a stall.
From the author's repo.

What it hooks into

  • session.startWhen a session starts
  • agent.spawnWhen a subagent starts
  • turn.stepAt each step of a turn
  • tool.callAround a tool call, where it can hold one
  • turn.completeWhen a turn ends
  • command.runWhen you run its slash command
  • ui.scrollA Claude Code eventPane
  • ui.renderDraws into the sessionPane

Read from the on() calls in its hook modules. Open its source under Files to check what each one does.

Files

The author's README and source, 4 files. They load when you open them.

Facts

Author
ice-lfernandes
Category
Workflow
Marketplace
lfernandes-mods
Repo
ice-lfernandes/claude-code-mods
Folder
agent-watch
Version
0.3.1
License
MIT
Repo stars
7
Last change
2026-10-09
Language
TypeScript
Files
13

Other mods in Workflow

launchpadice-lfernandesDraws a menu of installed commands, skills, and agents under the header, above the prompt, or in a pane, and a panel that sets the model and effort.plain-viewice-lfernandesHides successful tool rows and draws the agent's plan as a card above the prompt, with the current step and a summary when the turn ends.ide-modjkf87Opens an IDE window in the session, with an agent board, a file tree, and tabbed documents, and draws a usage gauge above the prompt.agent-discoverkeshrathOpens a pane to search, approve, and enable MCP servers through agent-discover, a local daemon any MCP host can share.flowctlMarcoFilho1Draws Claude Code's plan as a live graph in FlowCTL, a floating window: what is running, what comes next, and when a step needs you.panelinemarkneoninDraws a side pane of activity, files, agents, context, MCP, skills, and spend, plus a status line and a restyled chat.jev-searchmukiwuAnswers Claude Code's WebSearch with Jev Search, and sends each query to your Jev Search instance, jev.s1.dev unless you change it.flow-progresstassosgomesDraws a band above the prompt with TSG Flow's tasks done and its current phase. One mod inside my-skills.whats-agent-doingtzafrirDraws a box above the prompt that names the step Claude is on, how long it has lasted, and each background agent.allthingsallthingsweb-devRewrites each tool row as a verb, a slash, and its target, and draws the next allthings evening above the prompt, fetched from allthings.dev.agent-crewbekir1184Draws your subagents above the prompt as a pixel-art crew, with the current work, progress, time left, and tokens.typesafe-modBeLazy167Holds a commandWhen Claude asks you a this-or-that question, sends it to TypeSafe's Jev and draws the odds of each option beside the dialog.
All 396 in Workflow