Automated README summary
Automatically summarized from the README on 21 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Cordis plugin suite pairing Jev (TypeSafe System One decision models) with DeepSeek Harness (dsh). It adds semantic judgement dsh lacks: dynamic tool pruning, semantic dead-loop blocking, and a guard for high-risk execution.
How it uses Jev
Jev answers typed questions on harness state: loop-guard judges whether each step makes progress and blocks dead loops; safety-guard reviews shell and file operations and returns deny or ask; tool-pruner picks the top-K tools for the intent; skill-router names one skill; result-shaper keeps the informative middle.
Primitives:choicescorenoul
Technique worth stealing
Non-generative System One verdicts (~150 ms, ~$0.00013 per decision) replace sampling for fast, reproducible semantic decisions.
Try it
dsh plugin --profile add github:zhangxaochen/dsh-jev, then set TYPESAFE_API_KEY in $DSH_HOME/.env.
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 projectunclear0.54
- Shows a System One patternFound in material0.70
- Describes handling uncertaintyunclear0.43
- Reports measured numbersnot found in the excerpt0.12
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.25
- Is a replica of the modelnot found in the excerpt0.30
- Solves a common problem (0–2)score on a 0–2 scale1.08 / 2
- About JevFound in material0.98
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 21 Sept 2026.