Verification & Guardrails

Prose linter with local regex rules and Jev judgment rules per paragraph, as CLI, pre-commit hook, GitHub Action and Claude Code skill.

Local software factory running YAML pipelines of coding agents and shell steps, with a typesafe step for typed Jev judgments.

Claude Code Stop hook that uses Jev to catch turns ending half-done: no action, broken promises, unwatched work or wrong language.

CLI design and copy linter: mechanical checks block commits, while fuzzy taste checks go to Jev for probability-scored review notes.

Tool-call firewall for Claude Code hooks and MCP servers: Jev answers seven risk questions and code maps them to allow, ask or deny.

Zero-dependency HTTP traffic and bot defense gate that can escalate requests to Jev for five typed risk questions.

Linter that scores code comments on five heuristics with Jev and fails CI when comments fall below thresholds.

Claude Code hook that, when you write an LLM call or classifier, injects a three-way test: plain code, frontier model or Jev.

Bun-based MCP server wrapping Jev with compact answers and a code-computed act, review or abstain verdict.

Windows tool that reads the local WeChat chat, redacts it, and has Jev judge conversation stage, intent, tension and next action.

Offline linter and agent skill that checks Jev requests for badly designed questions before they come back confidently wrong.

CLI gate for X drafts: local hard secret checks, then Jev Noul questions with thresholds; exits non-zero to block posting.

Desktop app running coding agents in parallel git worktrees, with optional Jev judgments of each changed file against the task.

Chinese controlled-writing agent skill for technical reports with nine rules, using static checks plus a Jev semantic gate for certainty.

Small Python demos of Jev: parallel Noul ticket checks with measured speedup, and a three-way Choice citation and claim checker.

GitHub Action where an AI agent turns an issue into a PR behind guards, checks, a reviewer and a Jev gate that escalates when unsure.

Hackathon agent monitor that scores chains of sandboxed agent actions with Jev and escalates through a fixed L1-L5 containment ladder.

Semantic ArkUI linter for coding agents: a fact extractor finds candidate state bugs and a System One model judges each one.

Codex and Claude Code skills that narrow a repository locally and let Jev judge which candidate files the coding model needs.

Experimental lab for semantic business gates: each gate is an independent Jev Noul that code maps to NO, REVIEW or YES by threshold.

Experimental memory admission lab: Jev weighs a proposed memory against its source and a small policy says save, skip or defer.

CLI and GitHub Action that scores a code change's risk from policy rules plus Jev's semantic signals, and suggests checks and reviewers.

Claude Code PreToolUse quality gate where Jev scores drafts (such as SVG illustrations) before they are written and blocks substandard work.

Discontinued DeepSeek Harness decision layer whose policies let Jev only narrow permissions and fail closed; successor is jevcore.

Experimental Foreman derivative where Jev supervises a Codex worker via Vercel AI Gateway, with programmer-chosen acceptance commands.

Vercel Labs' tiny Zig coding agent, listed for a typesafe_permission_reviewer builtin that runs permission decisions through Jev.

Dependency-light Go linter that applies natural-language rules to code and documents using decision models like Jev or Clef.

Grok Bot preflight layer: local hard gates first, then Jev judges ambiguity and returns proceed, scope_down, ask_human or block.

Hermes Agent approvals provider where one Jev request answers six typed questions and code derives APPROVE, DENY or ESCALATE.

Example of Jev as a before-tool-call risk gate in a Google ADK agent, blocking tools when P(risky) passes a threshold.