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-review-checklistgit 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-review-checklist)<a href="https://agentmods.dev/skills/sethdford/claude-skills/architecture-review-checklist"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-review-checklist/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-review-checklist"><img src="https://agentmods.dev/badge/skills/sethdford/claude-skills/architecture-review-checklist.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 | $0.00607 |
| Opus 5 | $0.00016 | $0.00303 |
| Sonnet 5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
architecture-review-checklist 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 12d 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 Review Checklist
Establish standardized architecture review process with clear criteria and repeatable outcomes.
Context
You are conducting architecture reviews. Evaluate designs against principles, quality attributes, operational readiness. Use consistent checklist; document decisions and rationale.
Domain Context
Based on architecture review frameworks and governance:
- Design Review: Does proposed design align with principles? Are quality attributes met? Trade-offs understood?
- Operational Readiness: Monitoring, alerting, logging, runbooks documented? Disaster recovery plan? Capacity forecast?
- Security Review: Authentication, authorization, secrets management, data protection? Compliance with regulations?
- Cost Impact: Infrastructure cost projections? Optimizations considered? Budget alignment?
Instructions
-
Prepare Checklist:
- Alignment: Does design follow architecture principles?
- Quality Attributes: Addresses scalability, reliability, security, maintainability?
- Dependencies: External services, databases, message queues? All documented?
- Operations: Monitoring, alerting, logging, runbooks? On-call procedure?
- Testing: Unit tests, integration tests, chaos testing? Coverage adequate?
- Compliance: GDPR, CCPA, HIPAA? Data residency requirements met?
- Cost: Projected monthly cost? Optimization opportunities?
-
Conduct Review: Present architecture. Walk through checklist. Score each item: met, partially met, not met. Discuss gaps and remediation.
-
Document Decision: Record what's approved, what needs work, contingencies. Link to design document. Assign owners for open items.
-
Track Follow-Up: Monitor that remediation happens before deployment. Close items only after verification.
-
Iterate: If review uncovers major issues, schedule follow-up review. Use past reviews to improve checklist.
Anti-Patterns
- Reviews Without Teeth: Checklist completed, issues noted, nothing changes. Result: wastes time. Guard: Reviews block deployment; open items must be resolved or documented as accepted risk.
- Checklist Without Context: Rote questions without understanding trade-offs. Result: surface-level feedback. Guard: Reviewer understands domain; asks "why?" on answers.
- No Documentation: Verbal feedback, forgotten after meeting. Result: team doesn't know what was approved. Guard: Written decision with rationale; link to design docs.
- Infrequent Reviews: Only at major milestones. Result: missed issues accumulate. Guard: Reviews on feature gates, before production, monthly architecture sync.
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.
- 12d ago First seen · 54 lines · 32 tokens per session scan A 19718d478745
architecture-review-checklist is a skill published in the GitHub repository sethdford/claude-skills (41 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 607 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
cmd_flutter_review
Review Flutter/Dart code for idiomatic patterns, widget best practices, state management, performance, accessibility, and security. Invokes the flutter-reviewer agent.
cmd_code_review
Code review — local uncommitted changes or GitHub PR (pass PR number/URL for PR mode).
cmd_cpp_review
Comprehensive C++ code review for memory safety, modern C++ idioms, concurrency, and security. Invokes the cpp-reviewer agent.
cmd_go_review
Comprehensive Go code review for idiomatic patterns, concurrency safety, error handling, and security. Invokes the go-reviewer agent.
coding-standards
Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.
santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.