widescreen-research: Command for Claude Code

.claude/commands/games/feature-discovery.md

feature-discovery is a command for Claude Code from glassBead-tc/widescreen-research. It costs 0 tokens per session (3,949 once invoked), scanned C, original, MIT.

A command that develops several possible ways to implement a requested software feature, then compares them using a structured discovery process.

In plain words
What is it for?
It helps explore feature implementations with configurable rounds, diversity, explorer count, and approaches such as first-principles or analogy-based thinking.
Why use it?
It reduces the chance of settling on the first idea when a feature could be designed in different ways.

Command for Claude Code

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

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/feature-discovery.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 feature-discovery

README.md
[![agentmods](https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/feature-discovery/github.svg)](https://agentmods.dev/commands/glassbead-tc/widescreen-research/feature-discovery)
Your own site
<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.

agentmods 80×15 button for feature-discovery

Your own site · 80×15
<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>
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 3,949 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 $0.03949
Opus 5 $0.00000 $0.01975
Sonnet 5 $0.00000 $0.00790
Haiku 4.5 $0.00000 $0.00395

Measured 9d ago against content hash 3d1e913ce932, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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
.claude/commands/games/feature-discovery.md · 531 lines

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 feature
  • max_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"

Read the full file on GitHub · 531 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. 9d ago First seen · 531 lines · 0 tokens per session scan C 3d1e913ce932

Subscribe to this mod's changes

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.