--- title: "subagent-tuner" url: "https://claudemods.dev/en/builds/subagent-tuner-130cab" source: "https://github.com/Kruhlikau/subagent-tuner" source_type: "github" repo: "https://github.com/Kruhlikau/subagent-tuner" author: "Kruhlikau" author_handle: "Kruhlikau" stars: 0 category: "Multi-agent orchestration" categories: ["agents"] tags: ["hooks", "model-selection", "plugin", "reasoning-effort", "subagents"] permission_level: 2 scan_complete: true install: "claude plugin marketplace add Kruhlikau/subagent-tuner\nclaude plugin install subagent-tuner@subagent-tuner" added: "2026-10-12T14:59:55.156Z" updated: "2026-10-12T15:05:59Z" locale: "en" content_locale: "en" --- # subagent-tuner A Claude Code mod that picks the model and reasoning effort of every subagent, with a recommendation by task kind, a band above the prompt, and a saved default. ## Description subagent-tuner is a Claude Code mod that settles the model and reasoning effort of every subagent before it runs. It offers three modes: Manual, which asks you via a pane or dialogs; Auto, which applies your saved default or a recommendation without asking; and a recommendation table that maps task kinds (review/audit -> opus/high, implement -> sonnet/medium, explore -> haiku/low) to model and effort. A band above the prompt shows the mode and default; both persist across sessions. It reads only the Agent call's type, description, model, effort and prompt length, changes only the model and effort fields, and makes no network calls. Requires Claude Code 2.1.287 or later. ## Install ``` claude plugin marketplace add Kruhlikau/subagent-tuner claude plugin install subagent-tuner@subagent-tuner ``` ## Original README # subagent-tuner **A Claude Code mod that picks the model and reasoning effort of every subagent, so a review runs on Opus and a file search doesn't.** [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![Version](https://img.shields.io/badge/version-0.1.3-informational.svg)](CHANGELOG.md) [![Claude Code](https://img.shields.io/badge/Claude%20Code-2.1.287%2B-d97757.svg)](https://claude.com/blog/claude-code-mods) Recording from a real Claude Code session: in Manual a pick pane asks before the subagent runs; in Auto the saved default sonnet / high replaces the opus the agent asked for Recorded from a real Claude Code 2.1.295 session on Windows 11 with the mod installed from this repo (frames cropped, captions added). The band, full size: The tuner's band above the prompt: Tuner, Manual, Auto (active), default sonnet / high, Reset When the agent starts a subagent, the tuner settles its model and effort: by asking you, by a recommendation for the kind of task, or by your saved default. ## Install Inside Claude Code (2.1.287 or later): ``` /plugin install subagent-tuner --marketplace Kruhlikau/subagent-tuner ``` Answer `y` to add the marketplace and pick the **user** scope. It starts working in that session.
Other ways: two steps, the shell, or a local clone ``` /plugin marketplace add Kruhlikau/subagent-tuner /plugin install subagent-tuner@subagent-tuner ``` ```sh claude plugin install subagent-tuner --marketplace Kruhlikau/subagent-tuner ``` ```sh git clone https://github.com/Kruhlikau/subagent-tuner claude --plugin-dir ./subagent-tuner ``` Update with `/plugin marketplace update subagent-tuner`, then `/plugin update subagent-tuner@subagent-tuner`. Remove with `/plugin uninstall subagent-tuner@subagent-tuner`.
## What you see **The band above the prompt** holds the mode and your saved default. Click `Manual` or `Auto` to switch, click the model or the effort to cycle it (`rec.` means "use the recommendation"), `Reset` to clear the default. Both are kept across sessions. **Manual** (the default after install) asks before a subagent starts. On a terminal 144 columns wide or more the question is a pane beside the transcript: ``` general-purpose · explore wide Model: haiku ▾ Effort: low ▾ r: Run d: Run and save as default c: Cancel ``` On a narrower terminal it is a short chain of dialogs. A dismissed question starts the subagent with what was shown; nothing is ever held back. **Auto** never asks. Your saved default wins, even over a model or effort the agent set itself (say, a rule in `CLAUDE.md` that makes it pass `model: "opus"`). A field left at `rec.` keeps what the call set, else takes the recommendation. A toast says what was applied: `Subagent (overridden) -> sonnet/high`. ## The recommendation | Task kind (from the subagent's type, else its description) | Model | Effort | | --- | --- | --- | | review, audit, verify, adversarial, security | `opus` | `high` | | implement, build, fix | `sonnet` | `medium` | | explore, search, research | `haiku` | `low` | A prompt longer than 4,000 characters gets one step more effort. Any other task gets no recommendation and inherits the session's model and effort. ## Where it stays out of the way - **`claude -p` and SDK hosts:** nothing is changed, so scripted runs and evals measure what they ask for. - **Forks:** never touched; a fork ignores model and effort anyway. - **VS Code extension:** it can't show the band there, so it never asks and behaves as Auto. - **Manual:** a call that already set both its model and its effort goes through as set. ## What it can read, write and run - **Reads** each Agent call's subagent type, description, model and effort, and the length of its prompt. It never sends anything anywhere: no network calls. - **Changes** only the `model` and `effort` fields of Agent calls. - **Stores** the mode and the saved default in Claude Code's own plugin store. - **Runs** `sh` (macOS, Linux) or `powershell.exe` (Windows), only to wait for your answer in the pane: once to check which shell exists, then one waiting process per open pane. - **Writes** an empty sentinel file to `.waits/` in the plugin's own folder when you answer in the pane; the waiting process deletes it. ## Requirements Claude Code 2.1.287 or later (mods). Tested on 2.1.295 and 2.1.296 on macOS and on Windows 11 with Git for Windows' default settings. ## Troubleshooting - **Dialogs instead of the pane:** the terminal is narrower than 144 columns. Widen it or zoom out. - **Subagents still on Opus:** you are in Manual and the agent set the model itself, or Auto has no saved default for the model. Switch to Auto and set the default. - **An update didn't change anything:** run the update commands above. Claude Code runs the installed copy from its cache, keyed by version. - **Two bands or two toasts:** the mod is loaded twice, for example installed and also passed with `--plugin-dir`. Keep one. ## Develop ```sh git clone https://github.com/Kruhlikau/subagent-tuner && cd subagent-tuner claude plugin validate --strict . claude plugin test . claude --plugin-dir . ``` `hooks/register.tsx` holds every call on `$`; the other modules are pure. The tests run against a fake `$` in `hooks/harness.ts`. Once Claude Code has loaded the mod, `.claude-plugin/types/` holds the API types and `npx tsc -p .` type-checks it. Bump `version` in `.claude-plugin/plugin.json` with every change: installed copies are cached by version. ## License [MIT](LICENSE)