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-principlesgit 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-principles)<a href="https://agentmods.dev/skills/sethdford/claude-skills/architecture-principles"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-principles/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-principles"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-principles.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 | $0.00029 | $0.00614 |
| Opus 5 | $0.00015 | $0.00307 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
architecture-principles 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 10d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Principles
Establish foundational principles that guide architectural decisions and align organization.
Context
You are defining architecture principles for the organization. Create clear, memorable guidelines that inform decisions. Involve stakeholders from product, engineering, and operations.
Domain Context
Based on architecture governance frameworks (TOGAF, Gartner):
- Guiding Principles: High-level philosophy (e.g., "Cloud-first", "Stateless services", "API-driven")
- Decision Rules: Specific rules derived from principles (e.g., "Use managed databases not self-hosted" from "Minimize operational burden")
- Trade-off Hierarchy: When principles conflict, which takes priority? Performance vs Cost? Consistency vs Availability?
- Exemptions: Clear process to override principles; document why and remediation plan
- Communication: Memorability matters; short, actionable, memorable
Instructions
-
Identify Core Values: What matters to the organization? Speed of innovation? Cost efficiency? Security? Reliability? List top 3-5.
-
Derive Principles: Turn values into principles. "Speed of innovation" → "Ship independently without central coordination". "Cost efficiency" → "Use managed services to reduce operational overhead".
-
Make Principles Memorable: Use simple language. "Move fast with confidence" better than "Implement robust CI/CD pipelines". Acronyms help: KISS (Keep It Simple, Stupid).
-
Create Decision Rules: For each principle, what are concrete decisions? "Cloud-first" → "Use EC2 not on-prem", "Use Lambda for new services", "Data in S3 not shared NFS".
-
Communicate and Enforce: Share with teams. Use in architecture reviews. Celebrate adherence; discuss exceptions constructively. Update as organization evolves.
Anti-Patterns
- Too Many Principles: 20 principles, teams ignore most. Result: becomes noise. Guard: 5-7 principles max. Memorable, not exhaustive.
- Principles Without Teeth: Define but don't enforce. Result: ignored, no effect. Guard: Use in reviews; track compliance; discuss exceptions.
- Conflicting Principles: "Always use consistency" vs "Optimize for latency" without hierarchy. Result: confusion. Guard: Explicit trade-off hierarchy; example: consistency > cost > speed.
- No Updates: Principles defined 5 years ago; organization evolved. Result: misalignment. Guard: Review annually; update with changes in strategy.
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.
- 10d ago First seen · 48 lines · 29 tokens per session scan A a3cf4585e015
architecture-principles is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 614 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
videodb
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize…
lead-intelligence
AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, and personalized outreach. Use when the user wants to find, qualify, and reach high-value contacts.
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
team-builder
Interactive agent picker for composing and dispatching parallel teams.
cmd_aside
Answer a quick side question without interrupting or losing context from the current task. Resume work automatically after answering.
seo
Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.