Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An OpenCode plugin that integrates System One (Jev) judgments into agent sessions, adding screening, secret scrubbing, decision tools, commands, model routing, done-check, semantic search, approvals, and compaction for OpenCode users.
How it uses Jev
Jev answers typed questions about tool results, prompts, and session state: screening for junk/injection, scoring for approvals and done-check, ranking for model routing and search. Results gate tool output, route models, trigger probes, and drive compaction, with fail-closed behavior.
Primitives:choicescorenoul
Technique worth stealing
Fail-closed integration: every judged feature defaults to safe refusal on faults, with deterministic regex scrubbing and UI-only clean verdicts.
Try it
Add the plugin via `opencode plugin add github:atvari-eu/opencode-system-one` and restart OpenCode.
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 projectFound in material0.74
- Shows a System One patternnot found in the excerpt0.39
- Describes handling uncertaintyunclear0.40
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalnot found in the excerpt0.37
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.63 / 2
- About JevFound in material0.99
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 3 Nov 2026.