widescreen-research: Command for Claude Code

.claude/commands/games/code-review-game.md

code-review-game is a command for Claude Code from glassBead-tc/widescreen-research. It costs 0 tokens per session (4,203 once invoked), scanned C, original, MIT.

A structured code-review workflow for a pull request or branch that coordinates several reviewers and limits the number and depth of findings.

In plain words
What is it for?
Use it to review changes at a shallow, standard, or deep level with a time limit and a maximum number of concerns per reviewer.
Why use it?
It helps cover architecture and other important concerns without getting stuck on minor style debates or reviewing forever.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is glassBead-tc/widescreen-research's own configuration. It tells Claude Code how to work on widescreen-research itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything widescreen-research configures →

Reuse

Borrowing it

Nothing to install: this file belongs to glassBead-tc/widescreen-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/glassBead-tc/widescreen-research/main/.claude/commands/games/code-review-game.md
Clone the repo
git clone --depth 1 https://github.com/glassBead-tc/widescreen-research

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-review-game

README.md
[![agentmods](https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/code-review-game.svg)](https://agentmods.dev/commands/glassbead-tc/widescreen-research/code-review-game)
Your own site
<a href="https://agentmods.dev/commands/glassbead-tc/widescreen-research/code-review-game"><img src="https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/code-review-game.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,203 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.04203
Opus 5 $0.00000 $0.02101
Sonnet 5 $0.00000 $0.00841
Haiku 4.5 $0.00000 $0.00420

Measured 6d ago against content hash 39b5b033d2a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

code-review-game scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .code-review-game
.claude/commands/games/code-review-game.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/code-review-game

Game-theoretic code review protocol that prevents bikeshedding and analysis paralysis while ensuring comprehensive coverage through multi-agent coordination and progressive disclosure.

Usage

/code-review-game "[pr_url_or_branch]" [review_depth] [time_budget] [concern_budget]

Arguments

  • pr_url_or_branch (required): Pull request URL or branch name to review
  • review_depth (optional): "shallow" | "standard" | "deep" (default: "standard")
  • time_budget (optional): Time limit in minutes (default: 30)
  • concern_budget (optional): Max issues per reviewer agent (default: 5)

Algorithm

Phase 0: Initialize Review Arena

# Create review game state
mkdir -p .code-review-game/{agents,findings,auctions,phases}

# Initialize game state
cat > .code-review-game/state.json << 'EOF'
{
  "pr_url": "$PR_URL",
  "phase": 0,
  "time_remaining": $TIME_BUDGET,
  "total_concerns_raised": 0,
  "anti_patterns_detected": [],
  "review_coverage": {},
  "agents": {
    "architecture_guardian": {
      "expertise": ["design_patterns", "system_boundaries", "abstractions"],
      "concern_budget": $CONCERN_BUDGET,
      "severity_threshold": 7,
      "focus": "forest"
    },
    "security_auditor": {
      "expertise": ["vulnerabilities", "authentication", "data_flow"],
      "concern_budget": $CONCERN_BUDGET,
      "severity_threshold": 8,
      "focus": "critical"
    },
    "performance_profiler": {
      "expertise": ["complexity", "database_queries", "caching"],
      "concern_budget": $CONCERN_BUDGET,
      "severity_threshold": 6,
      "focus": "bottlenecks"
    },
    "user_advocate": {
      "expertise": ["api_design", "error_messages", "documentation"],
      "concern_budget": $CONCERN_BUDGET,
      "severity_threshold": 5,
      "focus": "experience"
    },
    "maintenance_prophet": {
      "expertise": ["code_clarity", "test_coverage", "dependencies"],
      "concern_budget": $CONCERN_BUDGET,
      "severity_threshold": 6,
      "focus": "future"
    },
    "chaos_monkey": {
      "expertise": ["edge_cases", "race_conditions", "failure_modes"],
      "concern_budget": $CONCERN_BUDGET,
      "severity_threshold": 7,
      "focus": "breaking"
    }
  }
}
EOF

echo "🎮 Code Review Game initialized"
echo "📋 Reviewing: $PR_URL"
echo "⏰ Time budget: $TIME_BUDGET minutes"
echo "🎯 Concern budget per agent: $CONCERN_BUDGET"

Read the full file on GitHub · 482 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 482 lines · 0 tokens per session scan C 39b5b033d2a0

Subscribe to this mod's changes

code-review-game is a command published in the GitHub repository glassBead-tc/widescreen-research (6 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,203 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.