Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Claude Code and Codex skill for teams doing long or multi-session planning. It captures directives verbatim as numbered anchors and mechanically checks both the plan and the delivered work against them, quoting your own words when drift occurs.
How it uses Jev
Each planning bead is judged against every anchor by three Jev questions: is the anchor relevant, does the bead address it, does it contradict it. The development gate adds a fourth question on whether compliance is evidenced. Answers are gated in code into one verdict per anchor; coverage is computed across beads.
Primitives:choicescore
Technique worth stealing
Gate orthogonal Jev answers in code into a single verdict per anchor, then pair each satisfied anchor with a deterministic check.
Try it
Install via the marketplace plugin, then run the plan-anchor-installer skill or uv run install.py with --dest and --tracker.
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 material0.95
- Shows a System One patternFound in material0.63
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.88
- Top-10 learning shortlist signalunclear0.48
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.37 / 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 3 Nov 2026.