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-briefgit 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-brief)<a href="https://agentmods.dev/skills/sethdford/claude-skills/architecture-brief"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-brief/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-brief"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-brief.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 | $0.00032 | $0.00681 |
| Opus 5 | $0.00016 | $0.00341 |
| Sonnet 5 | $0.00006 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
architecture-brief 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Brief
Create concise, executive-friendly summaries of architecture decisions and tradeoffs.
Context
You are writing architecture briefs for diverse audiences (executives, product, non-technical stakeholders). Explain decisions in business terms, not technical jargon. Emphasize impact on cost, speed, reliability.
Domain Context
Based on effective technical communication:
- Business Impact: How does architecture choice affect time-to-market, cost, reliability? Quantify where possible.
- Trade-offs: Every architecture choice sacrifices something. Explicitly state: "We chose X over Y because Z matters more."
- Risk Acknowledgment: What could go wrong? Residual risks accepted. Mitigation plans for critical risks.
- Assumptions: What's true about our context that makes this choice right? Different context, different choice.
Instructions
-
One-Pager Structure:
- Title: "API Gateway Architecture for Microservices"
- Problem: "Multiple services exposing APIs; no unified interface, inconsistent auth, no rate limiting"
- Decision: "Implement API Gateway (Kong/AWS API Gateway)"
- Rationale: "Centralizes auth, rate limiting, routing; 2-week implementation"
- Trade-off: "Extra hop in request path (5ms latency); operational overhead of new service"
- Success Metrics: "Consistent error responses, 99.9% uptime, < 50ms latency"
- Risks: "Gateway becomes bottleneck (mitigation: auto-scaling, load testing)"
-
Lead with Impact: Start with business outcome. "This choice enables us to scale to 10x users without tripling ops team."
-
Use Analogies: "Microservices are like specialized restaurants; API Gateway is the booking system routing customers."
-
Acknowledge Uncertainty: "Based on current traffic and team size. If traffic changes 10x, we'll revisit."
-
Make it Scannable: Bullet points, bold key decisions. Executives should understand main point in 2 minutes.
Anti-Patterns
- Too Technical: Explain implementation details, not impact. Result: non-technical readers lost. Guard: Lead with business impact; explain technical choice as supporting detail.
- No Trade-offs Acknowledged: "This is the best solution." Result: unrealistic, erodes trust. Guard: Always state what you're sacrificing; explain why.
- Vague Success Metrics: "It will be more scalable." Result: hard to measure success. Guard: Quantify: latency < 100ms, 99.99% uptime, < 5min deployment.
- No Assumption Statements: Assume everyone knows context. Result: brief is incomprehensible to new readers. Guard: Explain context explicitly.
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 · 54 lines · 32 tokens per session scan A 5708a97afc11
architecture-brief is a skill published in the GitHub repository sethdford/claude-skills (40 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 681 once invoked, about $0.0002 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.
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.
springboot-verification
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
cmd_evolve
Cluster MEMORY.md entries by theme and optionally generate SKILL.md drafts.