Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A DeepSeek Harness plugin that gates risky shell commands, trims unused tool schemas per session, prunes skill catalogs, and ranks glob results, all via one Jev connection. All features default off and fall back to native behavior on failure.
How it uses Jev
On a rule hit, Jev judges verdict/reason/severity from command text, description, working directory and optional session excerpt; denials are never softened. Jev also scores which tools a task needs, skill relevance, and glob path relevance. Results drive tools.restrict, catalog filtering, and path ordering.
Primitives:choicescore
Technique worth stealing
Ask the model once per session which tools are needed, then deny the rest so their schemas leave the request, with a tool_search escape hatch.
Try it
dsh plugin --profile add yy1588133/dsh-sensitive-guard, restart DSH, then set the TypeSafe API key in settings.
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 material0.64
- Shows a System One patternFound in material0.66
- Describes handling uncertaintyFound in material0.93
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolFound in material0.99
- Top-10 learning shortlist signalnot found in the excerpt0.17
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.23 / 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 4 Nov 2026.