effortless

https://github.com/user-attachments/assets/9b5af48e-2ad8-4826-9443-4aeea1306664

A Claude Code mod that picks the model and the reasoning effort for every prompt. Easy questions run on Haiku or Sonnet at a low effort; hard jobs get High on your own model, and you never touch the model or Effort control. In one long chat on Opus about half the replies ran on Sonnet or Haiku, roughly half the cost by our estimate. One bar above the prompt also shows how full the chat is, how long the prompt cache stays warm, and hands off or compacts in one click when a chat gets heavy.

Powered by Haiku 5.5

Haiku 5.5 costs about 75% less than Haiku 4.5, and Anthropic names compaction and quick, well-defined work among what it is built for. effortless uses it in three places:

Each can be switched off: Settings → Judge → Model, and Settings → Handoff → Compact with.

Install

Two ways. Both take a minute and need no terminal.

1. Ask Claude (easiest). Paste this into Claude Code and press Enter:

Install the effortless plugin for me: run `claude plugin marketplace add HeyCubit/effortless` and then `claude plugin install effortless@effortless`. When both succeed, tell me to run /reload-plugins.

2. Commands. Type these two lines in Claude Code's chat box:

/plugin marketplace add HeyCubit/effortless

/plugin install effortless@effortless

Or in a terminal, in one line:

claude plugin marketplace add HeyCubit/effortless; claude plugin install effortless@effortless

Then run /reload-plugins (or restart Claude Code). A short setup opens above the prompt: keep Haiku alone (one click, no key, runs on your own Claude login) or add Jev (a TypeSafe key, about 4x faster effort calls), lean cheaper or smarter, and pick how handoffs are written. Run /effortless setup to go through it again, or change any of it in ⚙.

Updates come to you: when a new version is out, a card above the prompt offers Update or Later. Update loads the new version in the chat you pressed it in, with nothing to type.

What the bar shows

Prefer it quiet? Settings → Customize has a Minimal look with no bar.

When a chat gets heavy

When the cache has gone cold on a big chat, the bar turns to ice with Compact and Handoff:

Handoff writes a summary of the chat and carries on in a clean one. Quick takes a few seconds; Full checks git and saves HANDOFF.md (or runs your own skill). Then clear and carry on, clear and wait, or keep the chat and copy.

Compact takes an optional note for what the summary should keep. Every compaction, also /compact and the automatic one, is written by Haiku 5.5 by default, which Anthropic recommends for compaction at a fraction of the chat model's price; if Haiku fails, Claude Code compacts as usual. Switch it in Settings → Handoff → Compact with.

The bar also warns when a chat is getting swamped (each message re-reads a lot of context), when a 5-hour or weekly limit passes 80% (with a Save mode that caps effort at Medium), and when your judge stops answering.

Settings

Haiku, and Jev if you add it

Haiku 5.5 runs on your own Claude login and needs no key. It always makes the handoff call: from 30% of context, every second message, it reads what the chat was for, the trail of topics, the last reply and how full the context is, and says a fresh chat would suit only for a clear reason. Then the Compact button turns into a lit Handoff with the reason. Want Handoff on the bar all the time? Settings → Handoff → Handoff button → Always.

Haiku also picks the effort, unless you add Jev, TypeSafe's faster judge (about 0.25 s against about 1 s). With a key, Jev answers the effort first and Haiku steps in whenever Jev is unsure. Run /plugin configure effortless@effortless in Claude Code, or use the setup guide or the Judge card in Settings.

A key set with /plugin configure is kept in Claude Code's secure storage. A key pasted in the setup guide or the Judge card is written in plain text to ~/.config/jev/.env (the file the jev skills read), never to a file of this repo. If Jev fails or takes longer than 3 seconds, Haiku judges that prompt and effortless tells you why once per session (out of credits, key rejected, no answer).

Short follow-ups such as "go", "ok" or "yes" keep the effort already picked and ask no judge.

Keys and trust

• The default judge needs no key: Haiku runs on your own Claude login.
• A key is only needed to add Jev. Enter it with /plugin configure, never on the command line, so it stays out of your shell history: Claude Code then keeps it in its secure storage. A key pasted in the setup guide or the Judge card is saved in plain text to ~/.config/jev/.env instead, so prefer /plugin configure on a shared machine.
• A key is sent only to TypeSafe, and to nothing else. Use a key with a spending limit if your provider offers one.
• Like any Claude Code plugin, this mod runs code on your machine. Its code is in hooks/: read it before you install if you do not know the author. The programs it starts are claude itself (to update or uninstall the mod when you press those buttons), git (to see if a new version is out) and, on Update, a plain file copy of the new version into the folder your open chat runs from.

What it saves, honestly

Measured over 80k requests of real Claude Code use, about 76% of the cost is the context being read back from the cache on every tool call, 16% cache writes and only 8% output. Effort mostly changes how many tool calls a prompt makes.

• Against a high default (high, xhigh) Auto saves a lot: a median xhigh prompt cost about three times a medium one.
• Against a medium default it mostly saves a few percent, and gives hard jobs high on their own.
• Keeping chats short and compacting before the cache goes cold often saves more than effort does. That is what the countdown is for.

Does the cheaper answer hold up?

node bench/quality.mjs answers 30 prompts on Opus and on the model a router would pick, then a blind grader compares them. On 2026-10-09 the cheaper answer was good enough in 28 of 30 against Opus at high effort and 27 of 30 against Opus at medium. It cost 60 to 78% less on the easy and normal prompts that moved down. Against Opus medium the whole mix came out only 7% cheaper, because hard prompts go to Opus at high effort. It was almost never better, often slightly worse, and Haiku on easy prompts is where it slips most. Prompts there start with no chat history, so a long warm chat saves less. One run, one grader, small set: the full tables and limits.

How often the judge is right

/effortless bench runs labelled prompts through each judge you have set up, using the same code a real prompt goes through, and scores them against a fixed effort. Each case lists the efforts a careful person would accept for that message on that m