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 sethdford/claude-skills --skill architecture-katagit clone --depth 1 https://github.com/sethdford/claude-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/sethdford/claude-skills/architecture-kata)<a href="https://agentmods.dev/skills/sethdford/claude-skills/architecture-kata"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-kata/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/sethdford/claude-skills/architecture-kata"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-kata.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 | $0.00027 | $0.00523 |
| Opus 5 | $0.00014 | $0.00262 |
| Sonnet 5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
architecture-kata 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 11d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Kata
Practice architectural design through structured, time-limited design challenges.
Context
You are working on architecture kata. Design a system within constraints (time, technology, team). Iterate on design, gather feedback, refine. Read problem statement and constraints carefully.
Domain Context
Based on architecture kata format (similar to code kata, but for design):
- Problem Statement: Requirements, constraints, scale, non-functional requirements
- Time Box: 30 minutes to 2 hours. Forces focus and trade-off decisions.
- Constraints: Limited technology choices, team size, deployment options. Realistic constraints teach design skill.
- Feedback: After kata, discuss solution with peers/mentor. Learn from different approaches.
Instructions
-
Read Problem: Understand requirements. What's the core business problem? What's the scale? What's non-negotiable?
-
Identify Constraints: Technology choices? Team size? Deployment platform? Time-to-market? These shape design.
-
Quick Design (15-30 min):
- Sketch components/services
- Identify data model
- Show communication patterns
- Call out risks/trade-offs
-
Document Decisions: Why this architecture? What trade-offs made? What would you do differently at 10x scale?
-
Discuss & Refine: Present to peer or mentor. What would they do differently? Why? Learn from different perspectives.
Anti-Patterns
- Analysis Paralysis: Spend 30 minutes debating one decision. Result: no design in time box. Guard: Make quick decisions; iterate after.
- Overengineering: Design for 100x scale when problem is tiny. Result: complex, doesn't teach. Guard: Design for stated requirements; note what changes at 10x.
- No Constraints: Assume unlimited budget/time/team. Result: not realistic. Guard: Use constraints to learn prioritization.
- No Discussion: Design alone, never discuss. Result: miss learning. Guard: Share, discuss, learn from others' approaches.
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.
- 11d ago First seen · 51 lines · 27 tokens per session scan A d4818b7a8ca5
architecture-kata is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 27 tokens to every session and 523 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
cmd_docs
Legacy slash-entry shim for the documentation-lookup skill. Prefer the skill directly.
code-tour
Create CodeTour .tour files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests.
documentation-lookup
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
explain-this
Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findings report. Use when the user asks to "explain this", "what am I being asked", "what's happening right now", "help me understand this", "what does…
understand-change
Teach the user to deeply understand a change through interactive tutoring: restating understanding, drilling into why/what/how, and quizzing until mastery. The active counterpart to a one-shot explanation. Use when the user asks to "understand this change", "teach me this change", "help me understand what changed"…
master
Turn reference docs into active mastery through retrieval practice, case binding, and scenario simulation. Combines Skycak (learning science) and Chin (expertise acceleration) frameworks. Use when you want to deeply learn material, not just read it.