🔓A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context.
// pluginsGhalebDweikat/⟨Python⟩★ 99◷ MIT[ claude ]
Projects tagged #jev
// jev (9)
🔓
🔓Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, che…
// securityleepokai/⟨JavaScript⟩★ 56◷ MIT[ claude ]
🔓Claude Code skill: hand bulk judgment calls to Jev. 86% fewer Claude tokens on a 12-task benchmark, up to 20x faster. One-line npx install.
// devtoolsUditAkhourii/⟨JavaScript⟩★ 36◷ MIT[ claude ]
🔓A Claude Code mod that uses TypeSafe's Jev to decide auto mode tool calls. 2x faster than the built-in classifier on the calls it decides.
// pluginsmadisonrickert/⟨TypeScript⟩★ 22◷ MIT[ claude ]
🔓Small, calibrated decision models on your own machine: systemone-compatible local server, 6 agent skills, Claude Code guard, MCP tools. Weights on Hugging Face.
// skillslawrence3699/⟨Python⟩★ 11◷ Apache-2.0[ claude ]
🔓Claude Code plugin: Jev for rule checks, verbatim compaction, and prompt routing
// plugins0x7067/⟨Python⟩★ 12◷ MIT[ claude ]
🔓Context-pruning proxy for Claude Code and Codex: Jev judges which history is still needed, measured not claimed. POC here now, heading soon into https://gith…
// devtoolscompozy/⟨TypeScript⟩★ 27◷ MIT[ claude ]
🔓An open-source, model-agnostic decision router for Claude Code and Codex.
// devtoolsruban-24/⟨TypeScript⟩★ 11◷ Apache-2.0[ claude ]
🔓Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command s…
// mcp-serversFrancoisChastel/⟨TypeScript⟩★ 12◷ MIT[ claude ]