Jev 101
Start Guides
Search
中文 EN

use cases agent-harness-supervisor

Agents ✦ 90outlineCommunity tooling — calibrate on your hooks

Agent harness supervisor

Who: Teams wrapping Codex/Claude Code/Pi-style agents. Steps: On turn/tool boundary ask parallel questions — skill Choice, action allow/ask/deny, stuck/slop/done Nouls → harness steers or blocks. Expected effect: cheap semantic supervisor around the agent (community cluster).

Source: DevMortimer/pi-warden ↗ Docs / source ↗
1

Treat this as an outline — adapt state and questions to your data.

2

Implement in code — call System One / Jev; compose answers yourself.

3

Gate on confidence — act, confirm, or escalate before side effects.

Outline sketch

Prompt 
Audience: teams wrapping Codex / Claude Code / Pi.
Steps:
1) On turn or tool boundary, snapshot recent actions + rules.
2) Parallel: skill Choice; action allow/ask/deny; Nouls stuck, slop, false_done.
3) Harness steers, warns, or blocks — worker model stays separate.
Expected effect: cheap semantic supervision (community cluster).

Needs access to: typesafe-sdkagent-hooks

Who it's for

Teams wrapping Codex/Claude Code/Pi-style agents

Steps / how it's set up

Sources: pi-warden · foreman · jev-review · awesome-jev-usecases · Harness.

Cover the six-guard surface in prose: done-claim, stuck-loop, slop, irreversible, exfil, off-track — each as its own Noul/Score with code-side policy.

Sources (wave-2 deepen)

Expected effect

Independent typed supervisor above workers; enforcement stays in the harness.

Unofficial outline for learning. Paraphrased from public docs and tutorials — not a production recipe. Review sources before you automate anything.