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 router for Claude Code subagent dispatches that picks an Anthropic model tier per task. It uses TypeSafe's Jev to score the task first, and documents measurements showing where the approach does not work.
How it uses Jev
Jev answers five atomic questions about the task: depth and breadth as 5-level scores, mechanical, irreversible and ambiguous as nouls. Code combines them into a need value (0.60*depth + 0.40*breadth - 0.25*mechanical) and maps it to opus, sonnet or haiku. Noul probabilities also gate downgrades and produce confirm/clarify advice.
Primitives:scorenoul
Technique worth stealing
Upgrades are ungated; downgrades must be earned, because a 5-level score reads as low confidence while its weighted value stays sound.
Try it
./route.py --default opus "<task>" to see one decision, or ./probe.py to check serviceable tiers.
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 material0.93
- Shows a System One patternFound in material0.76
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolFound in material0.64
- Top-10 learning shortlist signalnot found in the excerpt0.36
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 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.