What is subagent-effort?
subagent-effort is a Claude Code mod by anderson-spider that sets the reasoning effort of every native subagent call from Jev's rating of its task, leaving the model as it was, and keeps local records to compare efforts. It is listed under Agents & automation and has no public popularity data yet.
| Type | Claude code mod |
|---|---|
| Author | anderson-spider |
| Repository | anderson-spider/claude-mods |
| Popularity | no public popularity data yet |
| Category | Agents & automation |
| Security | Review before installing (64/100) |
| Rank | #2,609 of 5,272 Claude Code mods; #192 in Agents & automation |
| License | MIT |
| Last commit | 2026-10-18 |
| Hooks | 4 events |
| Sees | Agent calls |
| Draws on | nothing |
Is subagent-effort safe to install?
subagent-effort scores 64/100 on the MCPMods security check: Review before installing. Things to review: sends data over the network; writes files or config; reads environment variables. It passed 5 of 8 checks.
Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.
| Check | Result |
|---|---|
| Sends data over the network | Review |
| Starts no processes | Pass |
| Writes files or config | Review |
| Reads environment variables | Review |
| Only sees the events it hooks | Pass |
| Doesn't drive Claude | Pass |
| Passes claude plugin validate | Pass |
| Has an open-source license | Pass |
API calls in its code
| Call | What it means |
|---|---|
$.clock.after | |
$.command.register | |
$.env.get | reads env vars |
$.fs.exists | reads files |
$.fs.read | reads files |
$.fs.write | writes files |
$.http.fetch | network requests |
$.session.root | |
$.settings.read | reads settings |
$.ui.log | draws interface |
$.ui.toast | draws interface |
How do I install subagent-effort?
- Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
claude --version
- Read its footprint. This lists every event it hooks and every API call it makes, without running it.
git clone https://github.com/anderson-spider/claude-mods claude plugin validate ./claude-mods/plugins/subagent-effort
- Install it. Run this in your terminal, then /reload-plugins in an open session.
claude plugin marketplace add anderson-spider/claude-mods && claude plugin install subagent-effort@spider-claude-mods
Or ask Claude to set it up
Paste this into Claude Code and it installs subagent-effort for you:
Install the "subagent-effort" Claude Code mod from https://github.com/anderson-spider/claude-mods/tree/main/plugins/subagent-effort. Run claude plugin validate on it first and show me what it can access before you enable it.
More from anderson-spider/claude-mods
This repository has at least 9 Claude Code mods on MCPMods.
- chatgpt: Ask ChatGPT or generate requested images in a logged-in browser; save results locally. (High risk)
- codex-computer-use: Control native Mac apps through Codex, with per-app approval and /codex-cu on|off. (Review before installing)
- coolify: Read or change your Coolify instance (projects, applications, deployments) through its API, using the url and apiKey plu (Low risk)
- file-explorer: File tree pane that follows Claude's reads, edits and searches, with git status, search, preview and path references (Low risk)
- gitlab: Work on GitLab merge requests and pipelines of the current repository, picking the host and token from its git remote. (Review before installing)
- image-preview: See images in the terminal: thumbnails of what you paste above the prompt, and each image Claude reads drawn under its r (Review before installing)
- session-hud: A card above the prompt: model, context and cache; the five-hour and seven-day limits with their pace; the running subag (Low risk)
- spider-team: Read-only analyst, planner and reviewer subagents; Jev picks each one's model and effort from the task. (Review before installing)