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.
curl -O https://raw.githubusercontent.com/glassBead-tc/widescreen-research/main/.claude/commands/games/refactoring-game.mdgit clone --depth 1 https://github.com/glassBead-tc/widescreen-researchWrote 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.
[](https://agentmods.dev/commands/glassbead-tc/widescreen-research/refactoring-game)<a href="https://agentmods.dev/commands/glassbead-tc/widescreen-research/refactoring-game"><img src="https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/refactoring-game/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/glassbead-tc/widescreen-research/refactoring-game"><img src="https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/refactoring-game.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03754 |
| Opus 5 | $0.00000 | $0.01877 |
| Sonnet 5 | $0.00000 | $0.00751 |
| Haiku 4.5 | $0.00000 | $0.00375 |
Grade C, and why
refactoring-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 8d 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 .refactoring-game How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/refactoring-game
Execute a game-theoretic refactoring protocol that prevents perfectionism spirals while maintaining code quality.
Usage
/refactoring-game [codebase_path] [ship_deadline] [budget] [max_iterations] [confidence_threshold]
Arguments
codebase_path(required): Path to the codebase to refactorship_deadline(optional): ISO 8601 deadline (default: 4 hours from now)budget(optional): Energy units for refactoring (default: 100)max_iterations(optional): Maximum refactoring rounds (default: 5)confidence_threshold(optional): Quality threshold 0-1 (default: 0.8)comments(optional): developer comments on the task
Algorithm
Phase 0: Initialize Game State
# Create game state tracking
mkdir -p .refactoring-game
cat > .refactoring-game/state.json << 'EOF'
{
"round": 0,
"budget_remaining": $BUDGET,
"improvements": [],
"spiral_detections": [],
"commitment_level": 0,
"players": {
"perfectionist": { "satisfaction": 0.0, "weight": 0.8 },
"shipper": { "urgency": 0.5, "weight": 0.9 },
"maintainer": { "debt_concern": 0.7, "weight": 0.7 },
"user": { "patience": 0.9, "weight": 1.0 }
}
}
EOF
# Analyze codebase health
echo "🎮 Starting Refactoring Game for $CODEBASE_PATH"
echo "⏰ Ship deadline: $SHIP_DEADLINE"
echo "💰 Budget: $BUDGET energy units"
Phase 1: Codebase Auction Analysis
# Calculate refactoring bids for each component
echo "🔍 Analyzing codebase for refactoring candidates..."
# Find all source files and calculate pain metrics
find "$CODEBASE_PATH" -type f \( -name "*.js" -o -name "*.ts" -o -name "*.jsx" -o -name "*.tsx" \) | while read -r file; do
# Calculate complexity score
complexity=$(npx complexity "$file" 2>/dev/null | grep -oE '[0-9]+' | head -1 || echo "10")
# Calculate churn (number of commits)
churn=$(git log --oneline -- "$file" 2>/dev/null | wc -l)
# Search for bug-related commits
bugs=$(git log --grep="fix\|bug\|issue" --oneline -- "$file" 2>/dev/null | wc -l)
# Calculate bid (willingness to pay for refactoring)
bid=$(echo "scale=2; ($complexity * 0.4) + ($churn * 0.3) + ($bugs * 10 * 0.3)" | bc)
echo "{\"file\": \"$file\", \"bid\": $bid, \"complexity\": $complexity, \"churn\": $churn, \"bugs\": $bugs}"
done | jq -s 'sort_by(.bid) | reverse' > .refactoring-game/auction.json
echo "📊 Auction complete. Top candidates identified."
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.
- 8d ago First seen · 405 lines · 0 tokens per session scan C e572d0132100
refactoring-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 3,754 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.