33 online·4645 visitors
COMMUNITY OBSERVED

Jev Classifier

A tool-selection layer for Codex and Claude Code that filters the available tools before expensive model calls.

CODEX / CLAUDE CODEOFFICIAL TYPESAFE SKILLWORKFLOW CODE + DOCS

Overview & Result

jev-classifier brings Jev tool selection to Codex and Claude Code; the author says it reduces input-token usage substantially by selecting tools before the main coding-agent call.

How Jev fits in the loop

  1. The coding agent receives a user task and a catalog of tools or skills.
  2. Jev chooses the relevant bounded tool or skill.
  3. The coding agent executes with the selected context and handles failures or fallbacks.

How to reproduce

  1. Read the repository benchmark instructions and record the exact model, tool catalog, and task set.
  2. Run the full-tool-schema baseline and the Jev-filtered condition on the same tasks.
  3. Report token usage, selected-tool accuracy, latency, and false-selection cases separately.

Why this build matters

It addresses a practical scaling problem for coding agents: large tool registries consume context even when only one tool is relevant.

Limitations

  • The reviewed post does not expose the benchmark task set or the decision rubric.
  • Token savings can hide missed tools, so selection accuracy and fallback behavior must be measured.
  • The reported percentages are author-reported, not JevForAgents measurements.

Patterns