widescreen-research: Command for Claude Code

.claude/commands/games/virgil-protocol.md

virgil-protocol is a command for Claude Code from glassBead-tc/widescreen-research. It costs 0 tokens per session (1,684 once invoked), scanned A, original, MIT.

A framework for improving an existing product or implementation by first finding close matches and changing only what is necessary. Its 3% rule means preserving a familiar solution unless there is a strong reason to deviate.

In plain words
What is it for?
Use it to search for existing products, open-source projects, research methods, and design patterns, compare them with a target need, and justify any departure from a close solution.
Why use it?
It reduces unnecessary reinvention and makes the reasons for larger changes explicit.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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 →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is /[swarm-intelligence](../orchestration/swarm-intelligence.md) "evaluate existing code review tools".

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/virgil-protocol.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 virgil-protocol

README.md
[![agentmods](https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/virgil-protocol.svg)](https://agentmods.dev/commands/glassbead-tc/widescreen-research/virgil-protocol)
Your own site
<a href="https://agentmods.dev/commands/glassbead-tc/widescreen-research/virgil-protocol"><img src="https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/virgil-protocol.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 1,684 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.01684
Opus 5 $0.00000 $0.00842
Sonnet 5 $0.00000 $0.00337
Haiku 4.5 $0.00000 $0.00168

Measured 8d ago against content hash 2aeb2be7199b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

virgil-protocol 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 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.

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.

.claude/commands/games/virgil-protocol.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Virgil Protocol

A deliberate innovation framework based on Virgil Abloh's 3% Rule: find what already exists, understand why it works, then change only what must be changed—nothing more.

Core Principle

"You can become a designer by changing 3% of what already exists." — Virgil Abloh

In software: If you're reinventing the wheel, you need an exceptional reason to make even small changes.

Variables

INNOVATION_TARGET: $ARGUMENTS MAX_DEVIATION: 3% EXISTING_SOLUTION_THRESHOLD: 0.95 (95% similarity acceptable) JUSTIFICATION_REQUIRED: true FAMILIARITY_PRESERVATION: maximum

Protocol Phases

Phase 1: Exhaustive Discovery (Time-boxed: 40% of budget)

OBJECTIVE: Find existing solutions that do EXACTLY what we need

=> web_search_exa: Comprehensive product search
=> github_search_exa: Open source implementations
=> research_paper_search_exa: Academic approaches
=> company_research_exa: Commercial solutions
=> pattern_synthesizer: Extract common patterns

DISCOVERY CRITERIA:
- Functional match (core requirements)
- Technical match (architecture/stack)
- Scale match (similar use cases)
- Quality match (production-ready)

GATE: Have we found a solution that's ≥95% what we need?
- [ ] At least 3 existing solutions identified
- [ ] One solution meets all core requirements
- [ ] Implementation approach is clear
- [ ] No critical gaps in functionality

If GATE fails: Expand search or reconsider requirements

Phase 2: Deep Understanding (Time-boxed: 25% of budget)

OBJECTIVE: Understand WHY the existing solution works

-> Analyze architecture decisions
-> Map user experience flow
-> Identify design patterns
-> Understand technical trade-offs
-> Document cultural/market context

UNDERSTANDING CHECKLIST:
- [ ] Can explain every major design decision
- [ ] Understand the problem it originally solved
- [ ] Know why alternatives were rejected
- [ ] Identified what makes it successful

GATE: Do we truly understand this solution?
- [ ] Could rebuild it from scratch
- [ ] Know its limitations
- [ ] Understand its evolution
- [ ] Can articulate its philosophy

If GATE fails: More research needed

Read the full file on GitHub · 254 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. 8d ago First seen · 254 lines · 0 tokens per session scan A 2aeb2be7199b

Subscribe to this mod's changes

virgil-protocol 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 1,684 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.