Skip to content

Show HN: Decide – Jev decisions in the shell, scripts, and agent skills

Show HN thread for Decide, a tool for making Jev decisions from the shell, scripts and agent skills.

Discussiondiscussion

This summary is based on how curated lists describe the project; its README was not available to review.

Overview

This is a Hacker News Show HN thread titled 'Decide - Jev decisions in the shell, scripts, and agent skills'. The only list text is its opening line, 'All software makes decisions. Code handles the deterministic ones', implying a tool that hands the non-deterministic judgments to Jev from the command line and from agent skills.

No thread or repository content was fetched, so commands, exit-code behaviour and licence are unknown here. Similar tools in this directory include SemDecide and pydecide's decide CLI, though it is not confirmed which, if either, this thread describes.

What the decision model decides

TypeQuestionAnswers
OtherTyped Jev questions asked from shell scripts and agent skills(inferred)—

How it works

  1. Install the CLI
  2. Pipe text and a question from a script
  3. Branch on the typed answer

Strengths

  • Brings Jev into shell workflows, per the title

Caveats

  • Only the title and one line are available
  • Repository not identified

At a glance

Type
Discussion
Status
discussion
Runtime
CLI / agent skill

Use cases and integrations

How curated lists describe it

Frequently asked questions

What is Decide?

Per the title, a tool for Jev decisions in the shell, scripts and agent skills.

Where is it discussed?

news.ycombinator.com/item?id=49878492.

Is the code linked here?

Not in the available information.

Related projects

  • X post showing StarCraft: Brood War in WASM exposed as an MCP server, with Jev playing and still losing to a Zerg rush.

    Discussiondiscussion
  • Auto-updated bilingual leaderboard of Jev ecosystem projects, tutorials and discussions, discovered daily and sorted by GitHub stars.

    Projectproduction
  • Claude skill that gives a ten-line gut-check on whether Jev could help with what you are building, citing tested patterns.

    Agent skillbetaMarkdown
  • Thirty worked Jev uses in ten levels, from a smart if statement to a pi coding agent that writes its own Jev questions.

    ProjectbetaTypeScript
  • Agent skill that makes a coding agent try Jev first for bounded judgments like classify, rank or gate, and log each attempt.

    Agent skillbetaPython
  • ChatGPT-style web chat where every word of every reply is a Jev multiple-choice decision over a ~1,800-word vocabulary plus END.

    ProjectprototypeTypeScript