agent-watch
by Lucas Fernandes · ★ 7 · updated yesterday
Subagents at a glance: tokens per agent, a toast when one stalls, and a summary naming the heaviest agent when they finish
Install
/plugin marketplace add ice-lfernandes/claude-code-mods/plugin install agent-watch@lfernandes-modsThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
session.startagent.spawnturn.steptool.callturn.completecommand.runui.scrollui.render- API calls
$.agent.list$.clock.every$.clock.now$.command.register$.env.get$.prompt.fill$.session.usage$.state.get$.state.set$.ui.close$.ui.log$.ui.open$.ui.resolve$.ui.status$.ui.toast- Draws
Pane- Can see
subagent spawnsevery tool call- Reach
- level 1 of 3 writes the prompt boxreads env varsreads mod statedraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/ice-lfernandes/claude-code-mods
- Path in repo
agent-watch- Source commit
e0c376athe exact code the scan read- Author
- Lucas Fernandes @ice-lfernandes
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.
More from ice-lfernandes/claude-code-mods
allowlist-coach
ice-lfernandes/claude-code-mods
Counts permission dialogs per rule and, after repeated approvals, offers to add the rule to permissions.allow, asking before it writes
launchpad
ice-lfernandes/claude-code-mods
A menu of one-click actions under the header, above the prompt or in a pane, and a control panel from ◆ pad: model and effort in one click, this collection's mods, the shortcuts. Pick and order up to 8 with /pad configuration
limits-meter
ice-lfernandes/claude-code-mods
Plan limits and context above the prompt: model and effort, 5-hour and weekly windows with reset times, context fill, cache hit rate, tokens per turn, and a toast on a costly model switch near the limit
plain-view
ice-lfernandes/claude-code-mods
A quiet transcript: tool rows step aside and the agent's plan shows as a card above the prompt, with the current step, progress bars and a summary when the turn ends
test-hud
ice-lfernandes/claude-code-mods
Test runs at a glance: passing over total in the status line, a sparkline of failures across runs, the failing tests, and a toast when the suite turns green