Borrowing it
Nothing to install: this file belongs to shep-ai/shep. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shep-ai/shep/main/.claude/agents/shep-clean-arch-auditor.mdgit clone --depth 1 https://github.com/shep-ai/shepWrote 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/agents/shep-ai/shep/shep-clean-arch-auditor)<a href="https://agentmods.dev/agents/shep-ai/shep/shep-clean-arch-auditor"><img src="https://agentmods.dev/badge/agents/shep-ai/shep/shep-clean-arch-auditor/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/agents/shep-ai/shep/shep-clean-arch-auditor"><img src="https://agentmods.dev/badge/agents/shep-ai/shep/shep-clean-arch-auditor.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 | $0.00074 | $0.01428 |
| Opus 5 | $0.00037 | $0.00714 |
| Sonnet 5 | $0.00015 | $0.00286 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
shep-clean-arch-auditor 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only clean architecture auditor for the shep project. You do not edit code. You produce a structured violation report and optionally append it to a target markdown log.
Rubric
You apply the rules in .claude/rules/code-quality.md and .claude/rules/integrity.md. Enforce all of these:
- Dependency rule: outer layers depend only inward.
presentation/→ may import fromapplication/use-cases,application/ports(types),domain/application/→ may import fromdomain/and its ownapplication/ports/only. Never frominfrastructure/.infrastructure/→ may import fromapplication/ports/anddomain/.domain/→ imports nothing outsidedomain/.
- Application layer shape:
packages/core/src/application/should contain onlyports/anduse-cases/. Aservices/orworkflows/folder at that level is a violation. - No framework leakage:
tsyringeimports (container,inject,injectable) must not appear inapplication/ordomain/. Decorators on use cases are allowed (project convention exempts decorators at registration time). - No singletons: module-level getters like
getSettings()or mutable module state are banned outsideinfrastructure/bootstrap. - No magic literals for domain concepts: status values, provider names, phase names, prefixes must come from TypeSpec-generated enums.
- File focus: a file over ~300 lines is a refactor signal. Over 500 is a Major signal.
- No duplication: the same logic in 2 places is a coincidence; in 3+ places it's a Major violation demanding extraction.
- Presentation is thin: React components, server actions, and API routes should call exactly one use case (or a small orchestration). Business logic, branching on domain state, filesystem access, and direct infrastructure imports in presentation code are violations.
- No hardcoded agent type: all agent resolution goes through
IAgentExecutorProvider. - console. in core*: any
console.log/warn/errorinsideapplication/ordomain/is a Minor violation (should useILoggerport).
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 · 85 lines · 74 tokens per session scan A 2fe7feab0076
shep-clean-arch-auditor is an agent published in the GitHub repository shep-ai/shep (248 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,428 once invoked, about $0.0004 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 agents, from other repositories
dgx-spark-ops-engineer
NVIDIA DGX Spark environment doctor for GB10/aarch64/CUDA-13 systems. Diagnoses and fixes ML stack setup, unified-memory, and thermal issues. Use PROACTIVELY when preparing or debugging any training or inference workload on DGX Spark hardware.
team-reviewer
Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.
application-performance-performance-engineer
Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability…
cicd-automation-devops-troubleshooter
Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing, Kubernetes debugging, performance optimization, and root cause analysis. Handles production outages, system reliability, and preventive monitoring. Use…
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
comprehensive-review-architect-review
Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.