subagent-effort
by anderson-spider · ★ 0 · updated today
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.
Install
/plugin marketplace add anderson-spider/claude-mods/plugin install subagent-effort@spider-claude-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.starttool.callturn.completecommand.run- API calls
$.clock.after$.command.register$.env.get$.fs.exists$.fs.read$.fs.write$.http.fetch$.session.root$.settings.read$.ui.log$.ui.toast- Can see
Agent calls- Reach
- level 3 of 3 networkwrites filesreads filesreads env varsreads settingsdraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/anderson-spider/claude-mods
- Path in repo
plugins/subagent-effort- Source commit
ebbc758the exact code the scan read- Author
- @anderson-spider
- 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 anderson-spider/claude-mods
chatgpt
anderson-spider/claude-mods
Ask ChatGPT or generate requested images in a logged-in browser; save results locally.
codex-computer-use
anderson-spider/claude-mods
Control native Mac apps through Codex, with per-app approval and /codex-cu on|off.
coolify
anderson-spider/claude-mods
Read or change your Coolify instance (projects, applications, deployments) through its API, using the url and apiKey plugin options.
file-explorer
anderson-spider/claude-mods
File tree pane that follows Claude's reads, edits and searches, with git status, search, preview and path references
gitlab
anderson-spider/claude-mods
Work on GitLab merge requests and pipelines of the current repository, picking the host and token from its git remote.
image-preview
anderson-spider/claude-mods
See images in the terminal: thumbnails of what you paste above the prompt, and each image Claude reads drawn under its row in the transcript
session-hud
anderson-spider/claude-mods
A card above the prompt: model, context and cache; the five-hour and seven-day limits with their pace; the running subagents with their type, model and effort, and the tokens they used; what the last turn sent and added, edits and errors.
spider-team
anderson-spider/claude-mods
Read-only analyst, planner and reviewer subagents; Jev picks each one's model and effort from the task.
tailscale
anderson-spider/claude-mods
Read or change your tailnet through the Tailscale API using the apiKey plugin option.