Automated README summary
Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Drift is a hook-based guard for Claude Code and Codex sessions. It remembers the session goal and warns when prompts or assistant replies stray from it, helping developers stay focused on the original task.
How it uses Jev
Jev judges relevance of the session goal against each submitted prompt and final assistant reply, using conversational context. The returned probability feeds a running score; crossing thresholds triggers advisory warnings or opt-in blocking, and the result is used to decide whether to warn or block.
Primitives:score
Technique worth stealing
Running exponential score with configurable alpha, warning and blocking thresholds, and fail-open behavior on timeouts.
Try it
git clone, uv sync, export TYPESAFE_API_KEY, then add hooks to Claude Code or Codex config.
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 material0.62
- Shows a System One patternnot found in the excerpt0.21
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.33 / 2
- About JevFound in material0.95
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 6 Oct 2026.