Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ValorVie/custom-skillsnpx agentmods add skills/valorvie/custom-skills/ai-friendly-architectureWrote 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/skills/valorvie/custom-skills/ai-friendly-architecture)<a href="https://agentmods.dev/skills/valorvie/custom-skills/ai-friendly-architecture"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/ai-friendly-architecture/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/skills/valorvie/custom-skills/ai-friendly-architecture"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/ai-friendly-architecture.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 | $0.00074 | $0.01866 |
| Opus 5 | $0.00037 | $0.00933 |
| Sonnet 5 | $0.00015 | $0.00373 |
| Haiku 4.5 | $0.00007 | $0.00187 |
Grade A, and why
ai-friendly-architecture 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 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.
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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Friendly Architecture Guide
Language: English | 繁體中文
Version: 1.0.0 Last Updated: 2026-01-25 Applicability: Claude Code Skills
Core Standard: This skill implements AI-Friendly Architecture. For comprehensive methodology documentation, refer to the core standard.
AI Skills Hierarchy | AI 技能層級
This skill is part of a three-layer AI collaboration system:
| Layer | Skill | Question it Answers | 回答的問題 |
|---|---|---|---|
| Behavior (Immediate) | /ai-collaboration |
"How should AI respond accurately?" | 「AI 如何準確回應？」 |
| Configuration (Session) | /ai-instruction-standards |
"What to write in CLAUDE.md?" | 「CLAUDE.md 該寫什麼？」 |
| Architecture (Long-term) | /ai-friendly-architecture (this) |
"How to structure code for AI?" | 「如何讓專案對 AI 友善？」 |
Purpose
This skill helps design project architecture that maximizes AI collaboration effectiveness through explicit patterns, layered documentation, and semantic boundaries.
Quick Reference
Core Principles
| Principle | Description | Benefit |
|---|---|---|
| Explicit Over Implicit | Document behavior explicitly | AI understands without guessing |
| Layered Context | Multi-level documentation | Appropriate detail per task |
| Semantic Boundaries | Clear module boundaries | Independent analysis |
| Discoverable Structure | Self-documenting structure | Quick orientation |
Context Layers
| Layer | Token Budget | Content |
|---|---|---|
| L1: Quick Ref | < 500 | One-liners, API signatures, entry points |
| L2: Detailed | < 5,000 | Full API docs, usage examples |
| L3: Examples | Unlimited | Complete implementations, edge cases |
Recommended Structure
project/
├── .ai-context.yaml # AI context configuration
├── docs/
│ ├── QUICK-REF.md # Level 1 documentation
│ └── ARCHITECTURE.md # Level 2 documentation
├── src/
│ └── auth/
│ ├── index.ts # Entry point with module header
│ ├── QUICK-REF.md # Module quick reference
│ └── README.md # Module documentation
└── CLAUDE.md # AI instruction file
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 · 239 lines · 74 tokens per session scan A f52eaf753b16
ai-friendly-architecture is a skill published in the GitHub repository ValorVie/custom-skills (5 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 1,866 once invoked, about $0.0004 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
plan-growth-loop
Generate prioritized growth loops with implementation roadmaps based on codebase analysis. Use when the user says "plan", "growth loops", "prioritize", "what should I build", or "roadmap".
validate-loop
Check if growth loop requirements are actually implemented in the codebase. Use when the user says "validate", "check status", "skene status", "is it done", or "verify implementation".
c-calendar
View and create calendar events via gog (Google Calendar) or icalBuddy (Apple Calendar). Check availability, list upcoming events, create/update/delete events, and manage multiple calendars.
c-lockin
Lock In Mode — orchestrate distraction blocking, environment setup, and session tracking.
c-ai
Query LLMs from the CLI — pipe text for summarization, chat interactively, use local or cloud models with llm or aichat.
c-contacts
Access macOS Contacts app via AppleScript. No CLI tool needed.