Automated README summary
Automatically summarized from the README on 10 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
VexJoy Agent is a cross-harness coding-agent toolkit (43 agents, 45 skills, 71 hooks, 164 scripts) that maps plain-English requests to specialist agents, skills, and pipelines across Claude Code, Codex, Factory, Reasonix, and Antigravity CLI.
How it uses Jev
In `/d`, Jev classifies the request to select agent, skill, and pipeline, then checks that the proposed route preserves the requested outcome; dispatch is gated on a Jev receipt for that exact intent. Deterministic force-route rules bypass Jev. Intent-alignment judgments are logged to learning.db without raw request text.
Primitives:choicescore
Technique worth stealing
Gate dispatch on a Jev receipt that the proposed intent matches the restated requested outcome, keeping judge model separate from the executing agent.
Try it
Set JEV_TRANSPORT and AI_GATEWAY_API_KEY or TYPESAFE_API_KEY, then run ./install.sh and use /d.
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 projectunclear0.45
- Shows a System One patternunclear0.52
- Describes handling uncertaintynot found in the excerpt0.10
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.91 / 2
- About JevFound in material0.99
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 10 Nov 2026.