jevbooks

← All projects

super

mindlace/super

Claude Code plugin marketplace: supersonic build plugins and optional Jev judgments.

Agent Decisions0.93Runner-up: Verification & GuardrailsViewfinderFlight recorder
Automated README summary

Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Claude Code plugin marketplace with two plugins: supersonic (superconductor conducts multi-spec builds via operator subagents; supercomposer composes the design package) and superpowers-jev, which adds optional TypeSafe Jev typed judgments to superpowers and supersonic.

How it uses Jev

superpowers-jev adds Jev judgments at 13 decision points in superpowers and supersonic, shadow mode by default and failing open. Each point sends its assembled state and questions to the TypeSafe endpoint; in shadow mode the verdict is only logged next to Claude's in .superpowers/jev/log.jsonl and nothing acts on it.

Primitives:choicescorenoul

Technique worth stealing

Shadow-mode logging of Jev verdicts beside Claude's, with jev report showing agreement and confident-and-wrong rates before promoting points to on.

Try it

/plugin marketplace add mindlace/super then /plugin install superpowers-jev@super; set TYPESAFE_API_KEY or a key file.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectnot found in the excerpt0.06
  • Shows a System One patternunclear0.40
  • Describes handling uncertaintyFound in material0.88
  • Reports measured numbersnot found in the excerpt0.04
  • Is a runnable toolFound in material0.98
  • Top-10 learning shortlist signalnot found in the excerpt0.21
  • Is a replica of the modelnot found in the excerpt0.06
  • Solves a common problem (0–2)score on a 0–2 scale1.05 / 2
  • About JevFound in material0.97
Signals
Jev is core to the project0.06Shows a System One pattern0.40Describes handling uncertainty0.88Reports measured numbers0.04Is a runnable tool0.98Top-10 learning shortlist signal0.21Is a replica of the model0.0600.51Solves a common problem (0–2)1.05 / 2012

no-judgment band (0.40–0.60)

Design patterns
Flight recorder0.83Viewfinder0.71Questionnaire0.49Check-up0.37Funnel0.32Traffic light0.22Fail open, fail closed0.2200.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 19 Oct 2026.