Claude Code mod
subagent-effort
Run each subagent on any model (gpt-6, grok-4.7, ...) at any reasoning effort, through model and effort parameters on the Agent tool
Install
/plugin marketplace add HaoYan-A/claude-code-mods
/plugin install subagent-effort@claude-code-modsMods install like plugins. Run /reload-plugins or start a new session to load it.
What it can access
- Reach
- L0Draws and remembers: draws
- Sees
- Agent calls, subagent spawns
- Hooks
session.starttool.describetool.callagent.spawnturn.step
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
- HaoYan-A/claude-code-mods
- Folder
plugins/subagent-effort- Marketplace
claude-code-mods- Author
- HaoYan-A
- License
- MIT
- Last updated
- 2 October 2026
- Listed in
- awesome-claude-code-mods
FAQ
What is subagent-effort?
Run each subagent on any model (gpt-6, grok-4.7, ...) at any reasoning effort, through model and effort parameters on the Agent tool It is a mod for Claude Code, from HaoYan-A/claude-code-mods on GitHub.
What can the subagent-effort mod access?
Its widest reach is "draws and remembers" (draws). It sees Agent calls, subagent spawns. Like any mod, it runs with your permissions.
How do I install subagent-effort?
Inside Claude Code (v2.1.287 or later), run /plugin marketplace add HaoYan-A/claude-code-mods and then /plugin install subagent-effort@claude-code-mods.
More context & usage mods
study-latex
yeonwooook/claude-study-latex
Fills the gaps in the Claude desktop app's own math in the Code tab: rewrites \[...\], environments written without dollars and one-line $$...$$ into forms the app draws, tells Claude how to write math, and on Windows with MiKTeX compiles TikZ figures; built for students who study with Claude. A fork of zaahiral/claude-latex 0.5.0
subagent-monitor
enginahmetbodur/subagent-monitor
A live Subagents pane and band: session cost at API prices, token breakdown, and each subagent's model, effort, elapsed time, context, tokens and cost, with a click-through detail view.
stuck-detector
choaticpixels/HauntedClaudeMod
Notices when Claude repeats the same failing command or edit, warns you, nudges Claude to change approach, and stops runaway retry loops before they burn your tokens.
swear-slap
paragpandyareal/swear-slap
Swear at Claude and a cartoon hand slaps your screen. The message is never sent, so it costs nothing, and a polite version goes back in your prompt box. Nothing to install.
still-mods
stillgbx/still-mods
Personal mods above the prompt: plan progress bars and context, 5-hour and weekly usage meters
switchmod
ShreyanshPatidar/sangamind
SwitchMod: useful extras for Claude Code, each one a switch. A usage meter above the prompt, an output viewer for long results and images, secret hiding, a stop for repeated failures, a check before risky commands, a work log, and coordination between parallel chats. /switchmod turns each on or off.
Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.