CalibratedDecisions.

Repo · Coding & code review

claude-auto-effort

Claude Code mod where TypeSafe Jev rates, in about 200 ms before each turn, how much careful reasoning a prompt needs (0–3) and sets the effort level…

Open github.com ↗

From the repository

Claude Code mod: sets the effort for each prompt with Jev

How builders describe it

Claude Code mod where TypeSafe Jev rates, in about 200 ms before each turn, how much careful reasoning a prompt needs (0–3) and sets the effort level with smoothing; Claude Code port of pi-auto-effort sharing its questions, policy and settings file.

The decision Jev makes

Label a change, score its risk, pick the relevant file, or decide whether a coding agent should continue.

Where it fits

Code review and coding agents are full of small questions: is this change risky, what kind of fix is this, which file matters. These projects answer them with Jev and route the rest to people or bigger models. All 450 coding & code review projects →

Related projects