Automated README summary
Automatically summarized from the README on 1 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
loadout keeps coding-agent skills in a separate library and injects only the ones predicted to fit each prompt, for Claude Code and Codex users who install many skills.
How it uses Jev
A cheap System One model, Jev, predicts which library skills fit each substantive prompt; the prompt hook then adds those skills. The launcher instead makes one up-front decision per session covering skills, MCP servers and a model tier. About $0.001 per routing decision on the v4 benchmark.
Primitives:choice
Technique worth stealing
Keep skills out of the always-on listing and route them per prompt with a cheap model, so context cost scales with relevance rather than library size.
Try it
Node 22.12+, a TypeSafe API key and the claude or codex CLI; clone, npm ci && npm run build && npm link, then loadout init.
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 material0.78
- Shows a System One patternnot found in the excerpt0.13
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersFound in material0.70
- Is a runnable toolunclear0.50
- Top-10 learning shortlist signalnot found in the excerpt0.27
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.44 / 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 1 Nov 2026.