Automated README summary
Automatically summarized from the README on 30 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Claude Code plugin for people running Claude Code inside a Herdr pane. It hands subtasks to new Claude Code agents placed in Herdr panes beside yours, so you can watch or take over.
How it uses Jev
One Jev request per task answers which model (haiku, sonnet or opus) and how much effort (low, medium, high, xhigh or max). The answer becomes the agent's --model/--effort flags and is logged to decisions.jsonl. With --watch, Jev also scores whether the on-screen agent is struggling.
Primitives:choicescore
Technique worth stealing
Route each subtask with one Jev call, then log the answer and billed tokens so routing and cost can be checked from real runs.
Try it
claude plugin install jev-herdr@jev-herdr, or run scripts/pick_model.py "Add a --verbose flag to the CLI"
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 material0.81
- Shows a System One patternnot found in the excerpt0.25
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.83
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 2
- About JevFound in material0.97
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 30 Sept 2026.