Automated README summary
Automatically summarized from the README on 29 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A skill and MCP server for Claude Code, Codex and Hermes that gives a structured build/repair loop, routes models and skills, recommends Git steps, and uses Jev to settle small decisions before a large model runs.
How it uses Jev
Four MCP Gate tools ask Jev: gate_triage whether an event needs an agent, gate_verdict which review findings evidence already closes, gate_decide whether a question must reach the owner, and gate_pick which tool/skill/session fits. find_code.py also asks Jev to rank code-search chunks. Results gate or route large-model turns; failures are reported, never guessed.
Primitives:choicescore
Technique worth stealing
Gate large-model turns behind cheap typed decisions on compact state, keeping the expensive model out when a single decision settles it.
Try it
Set TYPESAFE_API_KEY, then run install.ps1 (Windows) or install.sh (Linux/macOS/WSL).
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 projectFound in material0.90
- Shows a System One patternFound in material0.86
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalunclear0.43
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.80 / 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 29 Oct 2026.