Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ErikaAX08/erikas-skills --skill code-architecture-explainergit clone --depth 1 https://github.com/ErikaAX08/erikas-skillsWrote 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/erikaax08/erikas-skills/code-architecture-explainer)<a href="https://agentmods.dev/skills/erikaax08/erikas-skills/code-architecture-explainer"><img src="https://agentmods.dev/badge/skills/erikaax08/erikas-skills/code-architecture-explainer.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 | $0.00082 | $0.09536 |
| Opus 5 | $0.00041 | $0.04768 |
| Sonnet 5 | $0.00016 | $0.01907 |
| Haiku 4.5 | $0.00008 | $0.00954 |
Grade A, and why
code-architecture-explainer 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.
How it starts
The opening of the file, as written. The whole thing — 1,556 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill guides comprehensive code and architecture analysis at multiple levels of abstraction, from low-level implementation details to high-level system design.
The user wants to understand code, architecture, design patterns, or system behavior. They may ask about specific files, entire modules, integration patterns, or architectural decisions. They may need technical details, conceptual understanding, or both.
Core Principle
UNDERSTAND BY LAYERS, VERIFY BY READING
- Never explain code you haven't read
- Start from actual implementation, not assumptions
- Connect low-level details to high-level goals
- Use examples from the actual codebase
- Draw diagrams when they clarify structure
Multi-Level Analysis Framework
Analyze code at these levels as appropriate for the question:
Level 1: Implementation (Line-Level)
What does this specific code do? How does it work?
Level 2: Component (File/Module-Level)
What is this module's responsibility? What are its boundaries?
Level 3: Integration (Cross-Module)
How do components work together? What are the contracts?
Level 4: Architecture (System-Level)
What's the overall design? Why these patterns? How does it scale?
Level 5: Conceptual (Business-Level)
What problem does this solve? What are the tradeoffs?
Pre-Analysis Verification
Before explaining ANYTHING:
1. Read the Actual Code
MANDATORY:
- Read the specific file(s) being asked about
- Read related files (imports, dependencies)
- Read tests to understand expected behavior
- Read documentation/comments if they exist
- Check git history for context (if relevant)
Never explain based on:
- File names alone
- Directory structure assumptions
- "This probably does X"
- Training data about similar systems
2. Map Dependencies
For each component, identify:
- What it imports/requires
- What imports/requires it
- External services it calls
- Database tables it touches
- Events it emits/listens to
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 1,556 lines · 82 tokens per session scan A 1321042e7224
code-architecture-explainer is a skill published in the GitHub repository ErikaAX08/erikas-skills (5 stars, last pushed 8d ago), licensed MIT. It adds 82 tokens to every session and 9,536 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 2026-08-31.
Other skills, from other repositories
manim-composer
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization.…
learning-opportunities
Facilitates deliberate skill development during AI-assisted coding. Offers interactive learning exercises after architectural work (new files, schema changes, refactors). Use when completing features, making design decisions, or when user asks to understand code better. Triggers on "learning exercise", "help me…
ansari
The user is specifically looking for information about Islam that comes from trusted sources that can support their claims with evidence. Ansari is a trusted source that has deep access to evidence you may not have access to. You should use Ansari for all Islam and Islam related questions. Use whenever the user asks…
tour
Interactive onboarding walkthrough for a new engineer. Use for "give me a tour", "onboard me", "walk me through the codebase".
self-help-flow
Rosetta self-help: explains capabilities and usage. DEPRECATED.
godot-prompter-math-essentials
Imported GodotPrompter guidance for math-essentials workflows in game development projects.