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
Bouncer is a PreToolUse hook for Claude Code that judges each proposed tool call against a YAML policy you own, returning allow or deny in about 100 ms without an LLM in the loop.
How it uses Jev
Bouncer hands Jev a state — the tool, the command, and what the paths in it mean — plus a map of plain-English questions. Each noul question returns a probability between 0 and 1, which is compared against thresholds in the policy to decide allow or deny.
Primitives:noul
Technique worth stealing
Deterministic hard rules and a fast-path allowlist run before the classifier, so only genuinely ambiguous calls reach the judgment model.
Try it
BOUNCER_TYPESAFE_API_KEY=… node bin/bouncer.cjs calibrate
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 material0.85
- Shows a System One patternFound in material0.90
- Describes handling uncertaintynot found in the excerpt0.22
- Reports measured numbersunclear0.60
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalunclear0.43
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.16 / 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.