by mralexivy
Automatic model and effort router for Claude Code. A free plugin that picks Haiku, Sonnet or Opus for each prompt, adds risk floors and a review workflow, and shows cache and context state. No key, no server.
Available after the catalog security scan passes.
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
# Add to your Claude Code skills
git clone https://github.com/mralexivy/AutoModeGuides for using ai agents skills like AutoMode.
See how AutoMode compares with popular alternatives.
A free, open source model router for Claude Code. It picks the right model and the right effort for every prompt.
On the website: the docs · the benchmark · how to reduce Claude Code costs · install guide · Claude Code routers compared · AutoMode vs effortless · AutoMode vs Claude Code Router · does switching models waste the cache?
Quick questions stay cheap. Hard jobs get the strongest model. Risky changes always get a review. Install it and it starts. You never touch the model or the Effort control again.
A community project. It is not Claude Code's built-in auto permission mode, and Anthropic does not make it. See the difference.
Paste these into Claude Code, one at a time, then run /reload-plugins:
/plugin marketplace add mralexivy/AutoMode
/plugin install automode@automode
| Without AutoMode | With AutoMode | |
|---|---|---|
| Model | One model for every prompt | Haiku for a quick fact, Sonnet for an edit, Opus for design and risk |
| Effort | You set it, and you forget to change it | A judge sets it for each prompt, in about a second |
| Risky changes | The same checks as a typo fix | Security, migrations and payments always get an independent review, on Opus when the diff shows critical risk |
| Big jobs | One long chat that does everything | A plan, build, verify and review workflow with six small agents |
| Prompt cache | A cold cache is a surprise bill | A countdown on the bar shows when the cache goes cold |
| Your setup | A login you already have. No key. No server. |
Three ways. Each takes about a minute.
1. Ask Claude (easiest). Paste this into Claude Code and press Enter:
Install the AutoMode plugin for me: run `claude plugin marketplace add mralexivy/AutoMode` and then `claude plugin install automode@automode`. When both succeed, tell me to run /reload-plugins.
2. Two commands. Type these in the Claude Code chat box:
/plugin marketplace add mralexivy/AutoMode
/plugin install automode@automode
3. One line in a terminal:
claude plugin marketplace add mralexivy/AutoMode; claude plugin install automode@automode
Then run /reload-plugins, or restart Claude Code.
There is nothing to turn on. AutoMode starts with every session after you install it and run /reload-plugins. It routes on whatever model the session uses, so you do not pick a special model.
/automode off. Start it again with /automode on."mode": "off" in your config.json, or set AUTOMODE_ROUTER=off./automode setup.Requires Claude Code 2.1.287 or later in the terminal. Mods are on by default from that version. The Desktop app needs 2.1.286 or later, and the VS Code extension needs 2.1.299 or later. Tested with Claude Code 2.1.318.
If you set CLAUDE_CODE_ENABLE_FUNCTION_HOOKS in an early build, remove it. Claude Code 2.1.287 and later ignores it.
If the mod does not load, Claude Code runs as usual and nothing breaks. To check that it loaded, run /plugin. A line under the tabs reads 1 mod active · automode.
Why no special model? AutoMode used to start only when the model ID ended in
[1m]. Claude Code 2.1.311 removes that suffix before a mod sees the model, so the rule never fired. The old rule is still there as"activation": "picker"inconfig.json, for builds that keep the suffix.
claude plugin uninstall automode@automode
State lives in ~/.claude/plugins/data/automode/. Delete that folder to remove it.
/plugin and disable it in the Installed tab. Or run /automode off for one session.--safe-mode."disableAllHooks": true in ~/.claude/settings.json.Every prompt takes the cheapest route that is still adequate. Code sets a floor for risky work, and the judge never lowers it.
One quiet line above the prompt, in your theme's colors. It reports what actually ran.
| On the bar | Means |
|---|---|
| High · Opus | The effort and the model for this prompt. Deciding… while the judge thinks. |
| ◔ 38% | How full the chat's context is. |
| cache 58:12 | Time until the prompt cache goes cold. After that, the next message pays full price to re-read the chat. |
| saved ~$0.38 | The estimated saving against the model the session started on. Right after a switch it reads ↺ $0.07 to pay back, until cheaper requests pay off the new model's cache rewrite. |
| a refactor across modules | Why the route was chosen. |
| Auto | Switches routing on or off for this session. |
| ⚙ | Settings. |
AUTOMODE_UI=off hides the bar. /automode details prints the same facts as text, and /automode help lists the commands.
AutoMode's hooks run in every session that loads the plugin. What AutoMode draws depends on the app:
| Where you run Claude Code | Routing and guardian | The bar above the prompt | /automode text |
|---|---|---|---|
claude in a terminal, including an editor's terminal |
Yes | Yes | Yes |
| The Code tab of the Desktop app (not a WSL session) | Yes | Yes | Yes |
| The VS Code extension chat panel (2.1.299 or later) | Yes | No. Claude Code does not draw the band above the prompt there. | Yes. Use /automode for the same facts. |
claude -p and the Agent SDK |
Yes | No | Yes |
| A WSL session in the Desktop app | No. Plugins are not available there. | No | No |
Source: Mods overview, where mods run.
Each prompt takes one of four paths:
am:run <request> for the automode:run workflow. Automatic entry is off by dAutoMode is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by mralexivy. Automatic model and effort router for Claude Code. A free plugin that picks Haiku, Sonnet or Opus for each prompt, adds risk floors and a review workflow, and shows cache and context state. No key, no server. It has 74 GitHub stars.
AutoMode's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/mralexivy/AutoMode" and add it to your Claude Code skills directory (see the Installation section above).
AutoMode is primarily written in TypeScript. It is open-source under mralexivy on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh AutoMode against similar tools.
No comments yet. Be the first to share your thoughts!