Claude Code mod
agent-efficiency
Tracks each subagent's model, tokens, tools and time, scores whether a cheaper model would have done, and keeps a bounded per-repo log under ~/.claude/agent-efficiency.
Install
/plugin marketplace add poppydad/agent-efficiency
/plugin install agent-efficiency@local-modsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L2Writes or runs: writes files, drives Claude, reads files, reads env vars, reads mod state, draws
- Sees
- subagent spawns, every tool call
- Draws in
Pane- Hooks
session.startcommand.runagent.spawntool.callturn.completeui.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
- poppydad/agent-efficiency
- Folder
.- Marketplace
local-mods- Author
- poppydad
- Last updated
- 12 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is agent-efficiency?
Tracks each subagent's model, tokens, tools and time, scores whether a cheaper model would have done, and keeps a bounded per-repo log under ~/.claude/agent-efficiency. It is a mod for Claude Code, from poppydad/agent-efficiency on GitHub.
What can the agent-efficiency mod access?
Its widest reach is "writes or runs" (writes files, drives Claude, reads files, reads env vars, reads mod state, draws). It sees subagent spawns, every tool call. It draws in Pane. Like any mod, it runs with your permissions.
How do I install agent-efficiency?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add poppydad/agent-efficiency and then /plugin install agent-efficiency@local-mods.
More context & usage mods
agent-deck
Prabal-Singh/claude-mods
A pane on the right that tracks this session's subagents as a tree: status, current action, files changed, tokens and cost
agent-parade
davep-s20/claude-mods
A side panel of animated avatars for the main agent and every subagent: what each is doing, its tokens and tools, and when it finishes
agent-deck
NeedSomeFoodMr/claude-mods
A pane showing the main loop and every subagent of the session as pixel crabs, each under its role's hat: a short name, role, model, plan progress, context fill, tokens, estimated cost and time, with totals on top and the finished ones kept below; while agents work, one line above the prompt says how the run stands.
agent-party
ytruong11201/claude-code-mods
Your running subagents as 16×16 pixel heroes above the prompt: their task, what they are doing, time, tokens, and a voice that tells their status
agent-context-pruner
9Tech-Solutions/agent-context-pruner
Replaces Claude Code's compaction summary with decision-model pruning: stale tool calls and results are dropped or truncated, everything kept stays verbatim.
agent-radar
fbrogno/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.
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.