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/hooks/README.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/readme)<a href="https://agentmods.dev/commands/glassbead-tc/widescreen-research/readme"><img src="https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/readme.svg" alt="Measured on agentmods" 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 | $0.03095 |
| Opus 5 | $0.00000 | $0.01548 |
| Sonnet 5 | $0.00000 | $0.00619 |
| Haiku 4.5 | $0.00000 | $0.00310 |
Grade A, and why
README scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deterministic Workflow Hooks for Game Commands
Problem Statement
The game workflows (Ulysses Protocol, Feature Implementation Game, etc.) have explicit stage gates but rely on agent inference to determine if criteria are met. This creates non-determinism where we want determinism.
Solution: Enforced Stage Gates via Hooks
Use Claude Code's hook system to programmatically validate gate criteria before allowing workflow progression.
Architecture
Game Workflow State (.game-state/)
↓
Pre/Post Tool Hooks
↓
Gate Validation Scripts
↓
PASS → Allow progression
FAIL → Block + Provide actionable feedback
Hook Configuration
Add to your Claude settings (~/.config/claude-code/settings.json or project-local):
{
"hooks": {
"PreToolUse": [
{
"matcher": "Write|Edit",
"hooks": [
{
"type": "command",
"command": ".claude/commands/games/hooks/validate-gate.sh"
}
]
}
],
"PostToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": ".claude/commands/games/hooks/record-action.sh"
}
]
}
],
"UserPromptSubmit": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": ".claude/commands/games/hooks/inject-game-state.sh"
}
]
}
]
}
}
Hook Types
1. Gate Validation Hooks (PreToolUse)
Purpose: Block actions that violate current stage gate requirements
Example: In Ulysses Protocol Phase 2, block implementation tools until planning gate passes
# .claude/commands/games/hooks/validate-gate.sh
#!/bin/bash
# Reads tool call from stdin, checks current game state, blocks if gate not passed
STATE_FILE=".ulysses-protocol/state.json"
if [ ! -f "$STATE_FILE" ]; then
# No active game, allow
exit 0
fi
# Read tool call from stdin
TOOL_INPUT=$(cat)
TOOL_NAME=$(echo "$TOOL_INPUT" | jq -r '.toolName')
CURRENT_PHASE=$(jq -r '.phase' "$STATE_FILE")
# Enforce phase gates
case "$CURRENT_PHASE" in
1) # Reconnaissance phase
if [[ "$TOOL_NAME" == "Write" ]] || [[ "$TOOL_NAME" == "Edit" ]]; then
GATE_PASSED=$(jq -r '.gates.reconnaissance.passed' "$STATE_FILE")
if [ "$GATE_PASSED" != "true" ]; then
# Block and provide feedback
cat << EOF
{
"block": true,
"message": "🚫 Gate Violation: Cannot proceed to implementation. Reconnaissance gate not passed.\n\nMissing requirements:\n$(jq -r '.gates.reconnaissance.missing[]' "$STATE_FILE")\n\nRun: /ulysses-gate-check to see status"
}
EOF
exit 1
fi
fi
;;
esac
exit 0 # Allow
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.
- 6d ago First seen · 491 lines · 0 tokens per session scan A 5c648ccd1f86
README 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 3,095 tokens. A static security scan graded it A with 0 findings. 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.