jevbooks

← All projects

phase-exit

Know-Me-Tools/phase-exit

Bounded, evidence-backed phase completion with Rust and TypeSafe Jev.

Agent Decisions0.49Runner-up: Verification & Guardrails
Automated README summary

Automatically summarized from the README on 16 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

Phase Exit makes a bounded completion decision against an explicitly adopted contract. A Rust engine checks artifact identity and evidence predicates; optional TypeSafe Jev judgments answer narrowly defined semantic questions. Node hooks and Agent Skills expose the decision to coding hosts.

How it uses Jev

Jev answers narrowly defined semantic questions about the adopted contract and evidence. The engine uses the returned judgments to inform the bounded completion decision. The README does not specify the exact state or question types passed to Jev.

Technique worth stealing

Bounded completion decision against an explicitly adopted contract, with evidence predicates and optional semantic judgments.

Try it

cargo build --locked --workspace; npm ci --ignore-scripts --no-audit --no-fund; npm run build:no-tests; npm run package:no-tests

View on GitHub

Start using Jev: API key and your first request →

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 projectnot found in the excerpt0.09
  • Shows a System One patternunclear0.50
  • Describes handling uncertaintynot found in the excerpt0.13
  • Reports measured numbersFound in material0.90
  • Is a runnable toolFound in material0.79
  • Top-10 learning shortlist signalnot found in the excerpt0.19
  • Is a replica of the modelnot found in the excerpt0.11
  • Solves a common problem (0–2)score on a 0–2 scale1.07 / 2
  • About JevFound in material0.82
Signals
Jev is core to the project0.09Shows a System One pattern0.50Describes handling uncertainty0.13Reports measured numbers0.90Is a runnable tool0.79Top-10 learning shortlist signal0.19Is a replica of the model0.1100.51Solves a common problem (0–2)1.07 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.2700.51

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 16 Oct 2026.