Verification & Guardrails

Jev-powered adversarial or advisory reviewer for the omp coding agent, plus a typesafe_ask tool, plan/stop gates and context compaction.

Unix-pipeable CLI for Jev and other System One models: ask questions, gate shell commands via exit codes, calibrate thresholds.

Claude Code hook where Jev reviews each tool call against risk, authorization and scope questions and a local policy returns allow or deny.

OpenClaw plugin that checks each outgoing agent message against its destination and blocks client names, credentials or internal hosts.

OpenCode 2 plugin that asks Jev six questions about every shell command (local or remote via FarHand) and prompts unless clearly safe.

Orca Lab plugin where Jev judges each agent command, passing routine ones, refusing dangerous ones and giving reasons for risky ones.

Fuzzy linter CLI that checks a code tree against plain-language rules in one markdown file, judged by Jev via a swappable interface.

Semantic code linter that reads each method with its callers and callees and asks decision models about defects, kind, line and severity.

Pi extension that turns what you say into structured runtime constraints and checks every side-effecting tool call against them.

Pi extension using Jev as a tool-call gate, a bash output judge and a jev_ask tool, in shadow mode by default and failing open.

Auto mode for Pi: deterministic policy first, then Jev judges escalated bash/write/edit calls, failing closed when undecidable.

Lean Pi supervisor: zero-token regex guardrails, done-check verification, per-turn routing and a Jev/Clef semantic slop gate on diffs.

Pi extension that checks proposed code edits against repository Markdown rules with Jev, reporting rule text and line ranges.

Jev Sentinel: guard for Pi, Claude Code and Codex that checks tool calls, tool outputs and replies, failing closed.

Pi package that gates pi-subagents dispatches with one Jev call against configurable rule sets and adds a jev_ask tool.

Advisory Jev sidecar for Pi: four pre-flight hazard checks before bash/write/edit and four diff-quality checks after edits.

Pi extension that auto-approves routine Bash commands via a System One model and escalates flagged ones, including obfuscated, to a human.

Minimal Pi permission gate: deterministic rules first, then a classifier answers allow, ask or deny per gray-zone tool call; fails closed.

Pi guardrails on pi-typesafe that steer the agent: Jev checks rule breaks, irreversible actions, stuck loops and unverified done claims.

GitHub Action that compiles .jev.yml rules into Jev questions and fails, comments on or passes a PR based on the numbers.

npm library where Jev judges whether an agent's recent steps are stuck on the same assumption; code returns CONTINUE, WARN, REPLAN or HALT.

Pi-based coding agent where Jev gates every tool call, picks the model tier, checks 'done' claims and trims tool output.

Pre-execution hook for coding agents that lets shell commands run, asks a human, or blocks them, with optional Jev classification.

Runtime verification framework that drives your real app to check a coding agent's 'done', returning pass, fail or cannot tell.

Ruff-style prose linter whose semantic rules each ask Jev a yes/no question about a paragraph, title or section, with tunable thresholds.

Go linter whose rules are plain-English questions: static analysis picks nodes, Jev answers a Noul about each one.

Streaming PII redaction library for TypeScript with 155 regex detectors, optional NER, and opt-in Jev confirmation before redacting names.

Node tool that crosschecks a folder of Markdown notes for contradictions and repeats, and ranks notes by any question, using Jev.

Prose linter for AI writing tells: regex handles 18, Jev judges 15 as Nouls in one call, shipped as a Claude Code Stop hook.

Rust CLI and Claude Code PreToolUse hook that scores one tool call as Auto, Review or Escalate using a typed decision backend.