Automated README summary
Automatically summarized from the README on 1 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Prompt Rejector screens prompts, skill files and MCP tool descriptions before an AI agent acts on them, combining deterministic security checks, TypeSafe AI Jev judgments and a configurable reasoning model. It is for developers and agents that call the scanner and act on its decision.
How it uses Jev
Jev identifies suspicious instructions that local rules miss, such as credential-exfiltration text inside a tool parameter description. The application then returns block with evidence at the offending path. A repeat uses the cached result. Installing the scanner does not automatically intercept tool calls; the application must call it and act on the decision.
Primitives:choice
Technique worth stealing
Combine deterministic checks with focused Jev judgments and a configurable reasoning model, then act on the returned decision.
Try it
git clone --branch main https://github.com/revsmoke/promptrejectormcp.git && cd promptrejectormcp && npm ci && npm run build && node dist/test/ai/historicalReplayTests.js
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 projectnot found in the excerpt0.26
- Shows a System One patternnot found in the excerpt0.22
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.10
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalnot found in the excerpt0.33
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.78 / 2
- About JevFound in material0.95
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 1 Oct 2026.