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 karsten-s-nielsen/mad-scientist-skills --skill architecture-auditgit clone --depth 1 https://github.com/karsten-s-nielsen/mad-scientist-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/karsten-s-nielsen/mad-scientist-skills/architecture-audit)<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/architecture-audit"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/architecture-audit/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/karsten-s-nielsen/mad-scientist-skills/architecture-audit"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/architecture-audit.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 | $0.00174 | $0.12838 |
| Opus 5.5 | $0.00070 | $0.05135 |
| Sonnet 5.5 | $0.00035 | $0.02568 |
| Haiku 4.5 | $0.00017 | $0.01284 |
Grade A, and why
architecture-audit 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 1mo 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 — 635 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Audit (beta)
A comprehensive architecture audit skill with two modes and a single tier:
Modes:
- Planning (before code exists) — architectural pattern selection, bounded context decomposition, dependency direction design, SOLID compliance strategy
- Audit (on existing code) — scanning for architectural drift, coupling violations, domain model anti-patterns, dependency direction violations, and structural decay
Single tier: Architecture analysis is methodology-based — the value is in the analytical framework (dependency graphs, coupling metrics, pattern detection), not in paid tooling. The few tools referenced (import-linter, deptry, Madge) are free/open-source.
Beta: This skill is under active development. Phase coverage and detection patterns will expand based on field testing. Findings should be reviewed with appropriate skepticism — architectural assessment requires more judgment than grep-based vulnerability scanning.
Core question: "Does the structure of this codebase support its evolution?"
Academic and practitioner foundations
This skill synthesizes eleven architectural traditions:
| Tradition | Key Author(s) | Core Contribution | Primary Phases |
|---|---|---|---|
| Hexagonal Architecture (Ports & Adapters) | Cockburn (2005) | Dependency inversion at application boundaries; driving/driven port distinction | Phase 2, Phase 3 |
| Domain-Driven Design | Evans (2003), Vernon (2013) | Bounded contexts, ubiquitous language, strategic/tactical patterns, aggregate design | Phase 4, Phase 5 |
| Clean Architecture | Martin (2017) | The Dependency Rule — source code dependencies point only inward; four concentric rings | Phase 2, Phase 3 |
| SOLID Principles | Martin (2000s) | Five object-oriented design principles for maintainable, extensible code | Phase 6 |
| Enterprise Integration Patterns | Hohpe & Woolf (2003) | Messaging patterns for distributed systems; Splitter, Aggregator, Content-Based Router, Pipes and Filters | Phase 4 |
| Coupling and Cohesion | Constantine & Yourdon (1979), Martin (package principles) | Afferent/efferent coupling, Stable Dependencies Principle, cohesion classification | Phase 7 |
| CQRS | Young (2010), Fowler | Separate read and write models; command handlers mutate state, query handlers are side-effect-free | Phase 2, Phase 8 |
| Event Sourcing | Young (2010), Fowler | Store domain events as the source of truth; derive current state by replaying events | Phase 2, Phase 8 |
| Twelve-Factor App | Wiggins (2011, Heroku) | Twelve principles for building portable, resilient, cloud-native applications | Phase 8 |
| API-First Design | Swagger/OpenAPI community | Design the API contract before implementation; spec drives code generation and testing | Phase 2, Phase 8 |
| Architectural Decision Records | Nygard (2011) | Lightweight documentation of significant architectural decisions with context, consequences, and status | Phase 9 |
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.
- 1mo ago Changed 1bbfe7735688
- 2mo ago First seen · 635 lines · 174 tokens per session scan A 6701cb9887e8
architecture-audit is a skill published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 174 tokens to every session and 12,838 once invoked, about $0.0007 per session on Opus 5.5. 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.
architecture-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| architecture-auditkarsten-s-nielsen/mad-scientist-skills | Skill | 3 | 1mo ago | MIT | A | 174 | Claude Code |
| auditjlifyio/wyx | Skill | 3 | 29d ago | MIT | A | 81 | Claude Code |
| refactorzircote-plugins/refactor | Skill | 2 | 5mo ago | MIT | A | 112 | Claude Code |
| releasehyhmrright/brooks-lint | Skill | 1.6k | yesterday | MIT | A | 135 | Claude Code, Codex |
| recipe-front-reviewshinpr/claude-code-workflows | Skill | 711 | 4d ago | MIT | A | 29 | Claude Code |
| new-skillhyhmrright/brooks-lint | Skill | 1.6k | yesterday | MIT | A | 145 | Claude Code, Codex |
| brooks-audithyhmrright/brooks-lint | Skill | 1.6k | yesterday | MIT | A | 143 | Claude Code |