jev-superpowers
Software development framework for coding agents that hands dependency vetting, completion gates and debugging decisions to Jev.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
jev-superpowers is described in directory listings as a software development framework for AI coding agents enhanced with Jev typed decisions. Rather than letting the agent judge everything in free text, it delegates specific checkpoints to Jev: vetting packages before they are added as dependencies, gating claims that a task is complete, and making debugging decisions.
The name suggests it builds on the popular superpowers skill framework for coding agents, though no README was available to confirm the structure, supported agents or installation. It is listed with an MIT licence. Details beyond the listing summaries are unknown.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Is this package safe and appropriate to add as a dependency?(inferred) | — |
| Yes / no | Is the task actually complete?(inferred) | — |
How it works
- Agent reaches a checkpoint (new dependency, claimed completion, debugging step)
- Jev answers a typed question about it
- Agent proceeds, blocks or investigates based on the answer
Strengths
- Typed gates at known failure points in agent workflows
- Typed answers are easier to branch on than free-text model output
Caveats
- No README available to verify details
- Supported agents and install path unknown
At a glance
- Type
- Library
- Runtime
- Agent skills framework
- License
- MIT
Use cases and integrations
How curated lists describe it
Coding agents: software development framework for AI coding agents that hands package vetting and completion gates to Jev typed decisions.
yibie/awesome-jevSoftware development framework for coding agents enhanced with Jev for dependency vetting, completion gates, and debugging decisions.
logicrw/awesome-jev-projects
Frequently asked questions
What does Jev decide here?
According to listings, package vetting, completion gates and debugging decisions.
Which coding agents does it support?
The listings do not say.
What licence is it under?
MIT, according to the listing.
Related projects
Auditable Zig terminal agent pairing Codex for coding with Jev typed preflight and postflight checks under deterministic policy gates.
CLIproductionZigSelf-hosted software factory running coding agents in microVMs with verification gates; offers optional DSPy/Jev task intake advice.
ServicebetaPythonOpen-source agent guardrails that use Jev or LAYA to check prompts, retrieved content, tool calls and outputs for injection and risk.
ProjectbetaPythonClaude Code plugin with nine Jev-judged gates for rules, scope, intent, completion and claims that escalate but never approve.
HookbetaTypeScriptClaude Code plugin that scores a turn's redacted diff on eight Jev risk axes at Stop and asks Claude to reinvestigate once if high.
ProjectbetaGoRisk gate for AI coding agents: Jev decides at five layers and Claude Code hooks enforce deny or ask deterministically.
ProjectbetaJavaScript