Automated README summary
Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A harness for LLM agents that screens tool output before the agent reads it. Two filters (relevance and injection) sit between the agent's tools and the agent. Tested with three agent models on three search-heavy test beds and AgentDojo.
How it uses Jev
Both filters ask Jev, a hosted classifier model, typed questions about each chunk of a tool output. The relevance filter keeps chunks that answer the agent's own question about the call. The injection filter withholds lines that try to give the agent a task the user did not ask for.
Primitives:choicescorenoul
Technique worth stealing
Using a hosted System One classifier to screen tool output for relevance and prompt injection before the agent reads it.
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 material0.89
- Shows a System One patternFound in material0.77
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolnot found in the excerpt0.16
- Top-10 learning shortlist signalunclear0.51
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.94 / 2
- About JevFound in material0.97
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 13 Oct 2026.