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
A Go approval gate for Claude Code. When the agent is about to run a tool, a hook intercepts the call, TypeSafe Jev reviews it, and a local policy returns allow or deny. Aimed at third-party API setups that cannot use the harness's own approval flow.
How it uses Jev
Each intercepted action is sent to Jev with the current-turn user messages, the redacted tool input, and verified facts. Jev answers a fixed set of questions — risk, authorization, hazards, scope. The local policy turns those answers into a binary verdict; if Jev cannot produce one, the call is allowed.
Primitives:choicescore
Technique worth stealing
A deny needs positive evidence: Jev down, timeout, bad response, missing key, or broken audit DB all allow, recorded incomplete.
Try it
go build -o bin/jev-approve ./cmd/jev-approve, then install with --harness claude-code and --project.
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 material0.83
- Shows a System One patternFound in material0.68
- Describes handling uncertaintyFound in material0.94
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.33
- Is a replica of the modelnot found in the excerpt0.15
- Solves a common problem (0–2)score on a 0–2 scale1.17 / 2
- About JevFound in material0.98
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.