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 that adds Jev decision points to an agent harness: a risk gate on tool use, prompt triage, agent-profile routing, and review triage, with every decision streamed as OpenTelemetry spans into the ECC session trace for Grafana/Tempo.
How it uses Jev
Jev answers typed questions at four points: PreToolUse risk gate (action allow/review/block plus irreversible, rule_violation, touches_protected, secret_exposure; risk = max, thresholds .85/.60/.35), UserPromptSubmit triage (task kind, risk, ambiguity, agent profile, memory relevance), CLI routing (--profile-only), and review triage (severity/actionable/in-scope). Results drive deny/ask/allow, injected context, and profile selection.
Primitives:choicescorenoul
Technique worth stealing
Derive OTel trace IDs as FNV-1a of the session id so Jev spans nest under the existing ECC session root without a shipper.
Try it
curl -fsSL https://raw.githubusercontent.com/srknkrbb/jev-ecc/main/install.sh | sh, then jev init in a 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-1.14.0- 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 material0.88
- Shows a System One patternFound in material0.82
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolFound in material0.94
- Top-10 learning shortlist signalunclear0.49
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.36 / 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.