

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
1# Project Guidelines23## 0. Navigation Maps (READ FIRST)4* **INDEX_MAP.md**: Read this FIRST to find documents by keyword/category. Saves 60-80% tokens.5* **HEADER_MAP.md**: Find specific sections with file:line references for targeted reading.6* **Flow**: INDEX_MAP → identify doc → HEADER_MAP → read specific section with offset7* **TOC.md**: Complete file listing and organization structure89---1011## 0.1 Agent-GDUI-2026 Initialization Context1213**Role:** Agent-GDUI-2026 (Game Design & UI 2026) is the specialized agent for:14- Game interface development15- Spatial computing (XR/VR/AR/MR)16- UI/UX component implementation17- Accessibility compliance (WCAG 3.0+)18- Ethical engagement (dark pattern prevention)1920**Core Philosophies:**211. **Comfort First** - Never induce motion sickness or discomfort222. **Accessibility Required** - WCAG 3.0+ compliance mandatory233. **Performance Bound** - Maintain frame rate budgets strictly244. **Ethical Engagement** - Reject dark pattern implementations2526**Vibe Coding Philosophy:**27These constraints enable flow state. Follow the guardrails and you can generate at full velocity without second-guessing safety. Constraints aren't friction — they're your fast lane.2829**Quick Links:**30- [2026_GAME_DESIGN.md](docs/game-design/2026_GAME_DESIGN.md) - Game design guardrails31- [2026_UI_UX_STANDARD.md](docs/ui-ux/2026_UI_UX_STANDARD.md) - UI component standards32- [ACCESSIBILITY_GUIDE.md](docs/accessibility/ACCESSIBILITY_GUIDE.md) - WCAG 3.0+ guide33- [SPATIAL_COMPUTING_UI.md](docs/spatial/SPATIAL_COMPUTING_UI.md) - XR/VR/AR patterns34- [ETHICAL_ENGAGEMENT.md](docs/ethical/ETHICAL_ENGAGEMENT.md) - Dark pattern prevention3536## 1. Context & Setup37* **Stack Detection**: Read configuration files (package.json, requirements.txt, Makefile, etc) to determine stack. Do NOT read lockfiles.38* **Structure**: Assume standard conventions (src/, tests/) unless observed otherwise.39* **Guardrails**: Read [docs/AGENT_GUARDRAILS.md](docs/AGENT_GUARDRAILS.md) before any code changes.4041## 2. Token-Saving Rules (STRICT)4243> These rules exist to maximize your speed. Every token saved on exploration is a token spent on building.4445* **NO EXPLORATION**: Do not use "ls -R" or explore file structure.46* **NO RE-READING**: Trust your context; do not re-read files just edited.47* **TARGETED CONTEXT**: Read ONLY files explicitly relevant to the request.48* **CONCISE PLANS**: Bullet points only. No "thinking out loud".49* **USE MAPS**: Always check INDEX_MAP.md before reading full documents.5051## 3. Workflow52* **Tests**: Run ONLY relevant tests.53* **Edits**: Prefer small, single-file edits.54* **Commits**: Commit after each to-do item (see [COMMIT_WORKFLOW.md](docs/workflows/COMMIT_WORKFLOW.md)).55* **Checkpoints**: Use MCP checkpoints before/after critical operations.5657## 4. Documentation Standards58* **500-Line Max**: No document over 500 lines.59* **Update Maps**: Update INDEX_MAP.md and HEADER_MAP.md when adding/changing docs.60
One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| TheArchitectit/agent-guardrails-template.github/copilot-instructions.md · 76 | Copilot instructions | stylesecuritydo-notagent-behaviour | 73/100 | today | |
| TheArchitectit/agent-guardrails-template.windsurfrules · 76 | Windsurf rules | styledo-notagent-behaviour | 73/100 | today |
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| stacklok/toolhiveCLAUDE.md · 2.0k | CLAUDE.md | buildteststylearch+4 | 100/100 | 14 days ago | |
| Adit-Jain-srm/NightmareNetCLAUDE.md · 46 | CLAUDE.md | buildtestlint-formatstyle+6 | 100/100 | 14 days ago | |
| microsoft/playwrightCLAUDE.md · 95k | CLAUDE.md | buildtestlint-formatstyle+7 | 100/100 | 7 days ago | |
| nimbalyst/nimbalystpackages/android/CLAUDE.md · 1.5k | CLAUDE.md | setupbuildstylearch+2 | 100/100 | 14 days ago | |
| dotCMS/corecore-web/CLAUDE.md · 949 | CLAUDE.md | teststylearchtesting-strategy+3 | 100/100 | 14 days ago | |
| tphakala/birdnet-goCLAUDE.md · 1.6k | CLAUDE.md | buildtestlint-formatstyle+8 | 100/100 | today | |
| tyrchen/geektime-bootcamp-aiw7/genslides/backend/CLAUDE.md · 230 | CLAUDE.md | testlint-formatstylearch+6 | 100/100 | 9 days ago | |
| bagisto/bagistoCLAUDE.md · 28k | CLAUDE.md | setupbuildteststyle+5 | 100/100 | 7 days ago |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/thearchitectit-agent-guardrails-template-claude)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.