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/feature-discovery.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/feature-discovery)<a href="https://agentmods.dev/commands/glassbead-tc/widescreen-research/feature-discovery"><img src="https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/feature-discovery/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/feature-discovery"><img src="https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/feature-discovery.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 | $0.03949 |
| Opus 5 | $0.00000 | $0.01975 |
| Sonnet 5 | $0.00000 | $0.00790 |
| Haiku 4.5 | $0.00000 | $0.00395 |
Grade C, and why
feature-discovery scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .feature-discovery How it starts
The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/feature-discovery
Generate diverse, high-quality feature implementations using game theory to escape the "first idea best idea" trap.
Usage
/feature-discovery "[feature_request]" [max_rounds] [diversity_weight] [explorer_count]
Arguments
feature_request(required): Natural language description of the desired featuremax_rounds(optional): Maximum discovery rounds before convergence (default: 3)diversity_weight(optional): How much to reward unique approaches 0-1 (default: 0.3)explorer_count(optional): Number of cognitive explorers (default: 6)
Algorithm
Phase 0: Initialize Discovery Game
# Create game state for tracking hypotheses
mkdir -p .feature-discovery/{explorers,hypotheses,auctions}
cat > .feature-discovery/state.json << 'EOF'
{
"round": 0,
"feature_request": "$FEATURE_REQUEST",
"diversity_weight": $DIVERSITY_WEIGHT,
"hypotheses": [],
"patterns_detected": [],
"auction_results": [],
"explorers": {
"first_principles": {
"style": "Build from fundamental constraints",
"bias": "over-engineering",
"strength": "novel solutions"
},
"analogical": {
"style": "Find patterns from other domains",
"bias": "force-fitting metaphors",
"strength": "creative connections"
},
"user_empathy": {
"style": "Start from user journey",
"bias": "feature creep",
"strength": "actual user value"
},
"technical_elegance": {
"style": "Seek architectural beauty",
"bias": "ivory tower syndrome",
"strength": "maintainable design"
},
"pragmatist": {
"style": "Ship it yesterday",
"bias": "technical debt",
"strength": "fast delivery"
},
"contrarian": {
"style": "Question all assumptions",
"bias": "analysis paralysis",
"strength": "hidden insights"
}
}
}
EOF
echo "🎮 Feature Discovery Game initialized"
echo "🎯 Goal: Discover optimal implementation for '$FEATURE_REQUEST'"
echo "⚖️ Diversity weight: $DIVERSITY_WEIGHT"
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.
- 9d ago First seen · 531 lines · 0 tokens per session scan C 3d1e913ce932
feature-discovery 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 3,949 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.