jevbooks

← All projects

doom-in-claude-code

abelardodiaz/doom-in-claude-code

Doom plays itself in a Claude Code pane: Jev picks goals, Claude narrates.

Game & Simulation0.72Runner-up: Agent DecisionsGhostwriter
Automated README summary

Automatically summarized from the README on 31 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A Claude Code plugin that runs ViZDoom with Freedoom in a terminal pane and plays it autonomously: code handles navigation and combat, Jev picks goals, Claude plans and narrates.

How it uses Jev

About 2.5 times per second, Jev receives the screen frame (JPEG 448x336) plus state as text and picks which goal to chase (key, switch, exit) by highest probability, requiring a 0.2 gap; it also rates the tactic (fight/dodge/advance), though since 0.5.0 code decides fighting.

Primitives:choicescore

Technique worth stealing

Shuffle the options on every call because Jev favors the first one, and fall back to scripted logic when the top-two probability gap is under 0.2.

Try it

/plugin install doom-pane --marketplace abelardodiaz/doom-in-claude-code, then /doom-setup, then /doom

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-1.14.0
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 projectunclear0.50
  • Shows a System One patternFound in material0.82
  • Describes handling uncertaintynot found in the excerpt0.05
  • Reports measured numbersFound in material0.79
  • Is a runnable toolunclear0.59
  • Top-10 learning shortlist signalnot found in the excerpt0.36
  • Is a replica of the modelnot found in the excerpt0.07
  • Solves a common problem (0–2)score on a 0–2 scale0.00 / 2
  • About JevFound in material0.95
Signals
Jev is core to the project0.50Shows a System One pattern0.82Describes handling uncertainty0.05Reports measured numbers0.79Is a runnable tool0.59Top-10 learning shortlist signal0.36Is a replica of the model0.0700.51Solves a common problem (0–2)0.00 / 2012

no-judgment band (0.40–0.60)

Design patterns
Ghostwriter0.79Funnel0.54Inspection0.52Menu0.25Traffic light0.25Check-up0.2100.51

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 31 Oct 2026.