Automated README summary
Automatically summarized from the README on 27 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jev-watch watches Codex, OpenCode or any coding CLI in the background. It detects looping, stalling or off-task drift, stops the worker, reports to a lead agent (Claude Code or you), and resumes the same session after a correction. Built for orchestrator/worker setups.
How it uses Jev
Every 45 seconds, local rules check for repeated errors, idle time and no file changes. If rules pass, one Jev question (Choice) asks whether the log shows looping, off_task or stalled. If Jev flags a problem, jev-watch stops the worker, prints a report and exits 2. Jev is skipped when the log hasn't changed.
Primitives:choice
Technique worth stealing
Use a cheap decision model as a watchdog between an expensive orchestrator and cheaper workers, so the orchestrator stays idle until a real decision is needed.
Try it
claude plugin marketplace add polaminggkub-debug/jev-watch; claude plugin install jev-watch@jev-watch; or npm install -g github:polaminggkub-debug/jev-watch
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 excerpt0.30
- Shows a System One patternnot found in the excerpt0.25
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.87
- Top-10 learning shortlist signalnot found in the excerpt0.22
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.12 / 2
- About JevFound in material0.97
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 27 Sept 2026.