Automated README summary
Automatically summarized from the README on 26 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Claude Code plugin marketplace that forks core-claude and herdr-agent-org, replacing two subprocess judgments with Jev calls, and bundles the herdr-side org-relay, org-waker and aw-context components so the repo is self-contained.
How it uses Jev
Jev runs only at rare event boundaries: jev-intent-gate (PreToolUse, judging whether a pinned dependency version is backed by a registry lookup) and jev-research-nudge (Stop, judging whether the last turn hedged a checkable fact); in herdr-agent-org, tier-gauge inside dispatch-worker and review-gate-check at accept. Each call sends state, fails open, is cached by request checksum, and logs one audit line.
Primitives:choicescorenoul
Technique worth stealing
Put a System One decision primitive only at rare event boundaries, never on the hot path, with fail-open, checksum caching and one audit line per call.
Try it
/plugin marketplace add skylence-org/claudecode-jev-marketplace, /plugin install core@claudecode-jev-marketplace, then /core:setup.
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 material0.94
- Shows a System One patternunclear0.55
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.91
- Top-10 learning shortlist signalnot found in the excerpt0.28
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.19 / 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 26 Oct 2026.