All projects

jevskill

lazniak/jevskill

Teach your coding agent to stop burning context. Jev (System One) via OpenRouter or TypeSafe: 325ms, 0.000013 USD per decision. A/B tested 99.3% fewer input tokens with accuracy up. Ships a reversible reduce and a ledger that learns when Jev pays off.

Python
Stars
4
Forks
1

Why it is listed

A coding-agent skill asks Jev to shortlist relevant lines from large logs before the agent reads them; the README’s savings figures are project-reported.

Related projects

  • agent-fastpath

    Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.

    Shared topics: agentic-ai, claude-code, codex, coding-agent

  • decide

    Bulk decisions for AI agents. Jev classifies files and logs; your agent reviews exceptions. Reproducible cost and quality benchmarks.

    Shared topics: classification, claude-code, codex

  • jevelry

    Use Jev everywhere to make & track decisions

    Shared topics: classification, claude-code, codex