What it is
limpet is a Stop hook for coding agents. You write completion rules in plain language; every time the agent is about to stop, limpet checks the stop against those rules and sends the agent back to work if a rule is violated.
How it uses Jev
On each stop, limpet reads the last 3 messages, this turn's tool calls, and the final message, then asks jev one yes/no question per rule in parallel. Each rule gets a probability; rules over threshold cause exit 2 with one line on stderr, so the agent keeps working.
Primitives:choice
Technique worth stealing
Judge plain-language stop rules with one yes/no question per rule over recent messages and tool calls, tuning for recall.
Try it
Install via Claude Code or Codex plugin, or clone and add a Stop hook running python3 ~/limpet/limpet.py.
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricyes0.89
- Shows a System One patternyes0.82
- Handles uncertaintyno0.05
- Measuredunclear0.45
- Runnableyes0.95
- Worth recommendingno0.29
- Model replicano0.03
- Problem scopescore on a 0–2 scale1.26
- About Jevyes0.97
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.