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
A DeepSeek Harness plugin that intercepts bash/pwsh tool calls before they run, judging whether they would irreversibly delete or overwrite real data, and returning allow/revise/block/escalate. For DSH users wanting a hard pre-execution safety net.
How it uses Jev
After offline static rules and a read-only pre-screen, Jev answers one yes/no question on the command text: will this irreversibly delete or overwrite the user's real data? Two thresholds split the probability into allow/revise/block; escalate comes from hard rules or spent retry budget. Results drive interception, downgrade templates, or human approval.
Primitives:choice
Technique worth stealing
Use a single calibrated yes/no question on command text, with thresholds, as a hard pre-execute hook rather than a model nudge.
Try it
Requires Node ≥ 20; zero runtime dependencies. See README for DSH mounting and `guard selftest`.
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 patternnot found in the excerpt0.24
- Describes handling uncertaintynot found in the excerpt0.26
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.15
- Is a replica of the modelnot found in the excerpt0.15
- Solves a common problem (0–2)score on a 0–2 scale1.29 / 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 31 Oct 2026.