Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An npm library and Claude Code plugin that replaces Claude Code's built-in compaction summary. It deletes tool calls and results Jev says are no longer needed, keeping all user and assistant text verbatim and in order.
How it uses Jev
For every non-pinned tool call, Jev gets two noul questions over the whole conversation state: should the call stay, and should the result stay verbatim. Decisions against keepThreshold keep, truncate, or remove each call and result; the message list is then rebuilt.
Primitives:noul
Technique worth stealing
Send the whole conversation as state, replacing each tool result with a short note, and ask per-call keep/drop questions.
Try it
npm install fast-jev-compaction, set TYPESAFE_API_KEY, then call compactMessages(transcript, options).
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 projectFound in material0.82
- Shows a System One patternFound in material0.64
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalunclear0.49
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.24 / 2
- About JevFound in material0.93
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 20 Sept 2026.