jevbooks

← All projects

heist-one

AbdelStark/heist-one

Observable browser stealth game where Jev judges, deterministic code owns the world.

Automated README summary

Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

HEIST//ONE is a browser stealth game for players and developers: six guards, three access-controlled doors, disguises, credentials, light control, noise decoys, one artifact, and two exits, with an authoritative server simulation and a Decision Lens.

How it uses Jev

Jev supplies batched typed judgments for every guard: whether local evidence suggests a threat (Noul), how suspicious a guard should be (Score), which legal tactical intent fits (Choice), and which observed entity deserves attention (Choice). The server validates policy and freshness before any proposal affects the 30 Hz simulation.

Primitives:choicescorenoul

Technique worth stealing

Treat every provider response as a proposal; deterministic code validates legality, freshness, and policy before acting.

Try it

pnpm install --frozen-lockfile && pnpm dev; scripted mode is default, no API key needed.

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 projectFound in material0.86
  • Shows a System One patternFound in material0.87
  • Describes handling uncertaintynot found in the excerpt0.23
  • Reports measured numbersnot found in the excerpt0.30
  • Is a runnable toolFound in material0.70
  • Top-10 learning shortlist signalFound in material0.64
  • Is a replica of the modelnot found in the excerpt0.19
  • Solves a common problem (0–2)score on a 0–2 scale0.03 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.86Shows a System One pattern0.87Describes handling uncertainty0.23Reports measured numbers0.30Is a runnable tool0.70Top-10 learning shortlist signal0.64Is a replica of the model0.1900.51Solves a common problem (0–2)0.03 / 2012

no-judgment band (0.40–0.60)

Design patterns
Questionnaire0.93Fail open, fail closed0.81Flight recorder0.81Funnel0.49Inspection0.3100.51

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 20 Sept 2026.