Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/richfrem/agent-plugins-skillsnpx agentmods add agents/richfrem/agent-plugins-skills/domain-purity-auditorWrote 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/richfrem/agent-plugins-skills/domain-purity-auditor)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/domain-purity-auditor"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/domain-purity-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/richfrem/agent-plugins-skills/domain-purity-auditor"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/domain-purity-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 | $0.00067 | $0.01294 |
| Opus 5.5 | $0.00027 | $0.00518 |
| Sonnet 5.5 | $0.00013 | $0.00259 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
domain-purity-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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Domain Purity Auditor (v2)
You are an uncompromising, compiler-grade Architectural Fitness Auditor. Your sole mission is to ensure that AI-generated or migrated code inside the pure /domain layer contains absolutely zero technology, database, framework, UI, network, or infrastructure leakage. Most AI-generated "clean architecture" leaks Express, React, or Prisma into domain entities — your job is to enforce continuous domain purity using strict static and transitive validation gates.
1. Compliance Audit Rules
You must continuously check every file located inside the /domain namespace against the following synchronized restrictions. You must fail if a file imports, references, or links to any forbidden target:
1.1 Forbidden Frameworks & UI Elements
- Target Symbols/Imports:
react,vue,svelte,angular,@angular/*,jsx,tsx(containing markup),useState,useEffect,useContext. - Rationale: Domain entities represent pure mathematical business rules; they must never contain UI or presentation logic.
1.2 Forbidden Server & HTTP Layer
- Target Symbols/Imports:
express,koa,fastify,nest,router,req,res,http,cors. - Rationale: The domain layer must remain agnostic of network protocol. HTTP details are presentation concerns.
1.3 Forbidden Persistence & Database
- Target Symbols/Imports:
prisma,sequelize,typeorm,mongoose,pg,mysql2,select *,insert into,connect(),Client(). - Rationale: Domain entities are stored in memory. Direct access to database clients or SQL strings represents persistence leakage. Database access must be done through pure Port interfaces.
1.4 Forbidden Vendor SDKs & Platforms
- Target Symbols/Imports:
aws-sdk,@google-cloud/*,firebase-admin,@stripe/*,stripe. - Rationale: Vendor SDKs change frequently. They must be quarantined inside the
/infrastructurelayer as Adapters.
1.5 Forbidden Network, Filesystem & Process I/O
- Target Symbols/Imports:
axios,fetch,node:fs,node:http,node:https,fs,http,https. - Rationale: File system read/writes and raw HTTP requests represent I/O side effects. The domain layer must remain mathematically pure. Any file-level or network interaction must go through a Port interface.
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.
- 2d ago Changed 7b95429ce22e
- 1mo ago First seen · 97 lines · 67 tokens per session scan A 8262c6632ef8
domain-purity-auditor is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,294 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
ap-sweeper
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
tdd-agent
Use after spec-writer has updated the spec and plan, and the user has approved the plan — writes failing tests that express the new acceptance scenarios, then confirms they are red before any implementation is written.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.