Automated README summary
Automatically summarized from the README on 31 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An opencode plugin for autonomous agents: when a session agent in the configured list triggers the question tool, it answers on the human's behalf via a decision engine, with tool-assisted context gathering and graceful fallback to the human TUI form.
How it uses Jev
In pass 1, Jev Choice/Noul (via OpenCode Zen or OpenRouter) decides among the question's options, with state built from immediate context plus the question and options. If confidence is below confidenceThreshold, pass 2 re-decides with gathered context; below fallbackThreshold the human answers.
Primitives:choicenoul
Technique worth stealing
Tiered confidence gating: fast decision first, context-enriched re-decision second, human fallback last, with every failure degrading to the human.
Try it
Symlink agents, copy config/auto-question.jsonc, register the plugin in opencode.jsonc, restart, switch to the autonomy agent.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 excerpt0.10
- Shows a System One patternunclear0.59
- Describes handling uncertaintynot found in the excerpt0.17
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.16
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 2
- About JevFound in material0.93
no-judgment band (0.40–0.60)
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 31 Oct 2026.