A Jev agent folder that makes Claude write only, not decide
The author built a directory setup where Claude only generates text while Jev handles routing, relevance and completion judgments, code executes the actions and every step leaves a decision receipt, at $0.42 per 10,000 decisions.
I STOPPED LETTING CLAUDE MAKE DECISIONS THE DAY I BUILT THIS JEV AGENT FOLDER I used to let Claude decide, write and act on every single step -> now Claude only writes. Jev makes the calls, code does the acting, and every step leaves a receipt here's what's inside the folder: • the input > AGENTS.md - when to call Jev, when to skip it > state/build_state.py - goal, workers, done, missing, constraint. evidence, never a summary • Jev decides (questions/) > http://route.py - which model tier gets the task > next_worker.py - which worker acts next > http://relevance.py - keep or drop each tool output > http://done.py - is the goal actually met > http://risky.py - does this send, pay or delete? • code acts (rules/) > hard_rules.py - stop after ten actions, never publish unapproved > thresholds.yaml - act only on confident answers. fraud needs 0.95 • Claude writes (workers/) > http://research.py - sources and notes > http://writer.py - drafts and briefings > the only place in the whole folder where text gets generated • the proof > receipts/decisions.jsonl - options offered, chosen id, re-check, fallback > evals/ - dozens of my own labelled traces, thresholds tuned on them • the guards (hooks/) > pre_tool_use.sh - every command checked before it runs > http://stop.sh - checks "all done" before the agent is allowed to stop 10,000 decisions for $0.42. median 300 ms an LLM writes, Jev decides, code acts
This post quotes another post: x.com/polydao/status/2103689373774483815