leftspace89

Jev Why — AI skill for Claude Code

AI community

Show why the last sub-agent dispatch ran on the model it did.

How to install Jev Why

Installs to ~/.claude/skills/leftspace89-jevsubrouter-jev-why/SKILL.md

Terminal

mkdir -p ~/.claude/skills/leftspace89-jevsubrouter-jev-why && curl -fsSL https://raw.githubusercontent.com/leftspace89/jevsubrouter/HEAD/commands/jev-why.md -o ~/.claude/skills/leftspace89-jevsubrouter-jev-why/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Jev Why does

description: Show why the last sub-agent dispatch ran on the model it did

Run the report below and show the user its output verbatim inside a fenced block. Do not paraphrase the numbers or re-derive the decision.

!`node "${CLAUDE_PLUGIN_ROOT}/bin/jevsub.mjs" why $ARGUMENTS`

`Jev chose` is the raw answer with its confidence and the probability spread across the tiers. `Policy` is what the local rules did with it. `Dispatched on` is the model the worker actually ran on. Pass `--turn` to

Alternatives in AI

Agentlas Orch — Set or show which model runs the orchestrator and which runs the workers 1.1k ★
Agentty — AI pair programming in your terminal — one static binary, sub-ms startup, any model 597 ★
Upstream Watch — Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict 361 ★