Automated README summary
Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An MCP server and browser tool for Claude Code, Cursor, Codex and other MCP clients. It reads a large PDF, Word or Excel file locally once, then answers questions with cited passages and exact spreadsheet calculations, saving tokens and time.
How it uses Jev
For each question, Reader finds up to 20 candidate passages and makes one Jev call with typed relevance checks. Jev judges which passages answer the question, whether they disagree, contain hidden instructions, or support no answer, producing verdicts like answer_from_passages, not_in_document or low_confidence that the AI uses to answer only from cited evidence.
Primitives:choicescore
Technique worth stealing
Use one batched Jev call with typed relevance checks over candidate passages to filter evidence and produce calibrated verdicts instead of putting the whole document in context.
Try it
Install via npx @readycode/reader as an MCP server, set OPENROUTER_API_KEY, then ask your AI to load a document and answer questions.
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 projectunclear0.58
- Shows a System One patternunclear0.48
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.98
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.24
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.41 / 2
- About JevFound in material0.77
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 23 Oct 2026.