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 agentmods add rules/savagelysubtle/big-brain-memory-bank/1002-python-clean-architecturegit clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-BankWrote 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/rules/savagelysubtle/big-brain-memory-bank/1002-python-clean-architecture)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/1002-python-clean-architecture"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/1002-python-clean-architecture.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02091 |
| Opus 5 | $0.00000 | $0.01045 |
| Sonnet 5 | $0.00000 | $0.00418 |
| Haiku 4.5 | $0.00000 | $0.00209 |
Grade A, and why
1002-python-clean-architecture 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 4d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN writing Python code ENSURE it's placed in the correct layer according to clean architecture principles globs: src/the_aichemist_codex/**/*.py
<layer name="application">
<responsibility>Orchestration of domain objects to execute business use cases</responsibility>
<allowed-dependencies>domain</allowed-dependencies>
<directories>
<directory>application/commands</directory>
<directory>application/dto</directory>
<directory>application/exceptions</directory>
<directory>application/handlers</directory>
<directory>application/mappers</directory>
<directory>application/queries</directory>
<directory>application/services</directory>
<directory>application/use_cases</directory>
<directory>application/validators</directory>
</directories>
</layer>
<layer name="infrastructure">
<responsibility>Implementation of interfaces defined in domain using external libraries and frameworks</responsibility>
<allowed-dependencies>domain, application</allowed-dependencies>
<directories>
<directory>infrastructure/ai</directory>
<directory>infrastructure/config</directory>
<directory>infrastructure/fs</directory>
<directory>infrastructure/notification</directory>
<directory>infrastructure/parsing</directory>
<directory>infrastructure/utils</directory>
</directories>
</layer>
<layer name="interfaces">
<responsibility>Delivery mechanisms and adapters that connect the application to external systems</responsibility>
<allowed-dependencies>domain, application</allowed-dependencies>
<directories>
<directory>interfaces/api</directory>
<directory>interfaces/cli</directory>
<directory>interfaces/events</directory>
<directory>interfaces/ingest</directory>
<directory>interfaces/output</directory>
<directory>interfaces/stream</directory>
</directories>
</layer>
<layer name="cross_cutting">
<responsibility>Concerns that span multiple layers</responsibility>
<allowed-dependencies>limited to specific needs</allowed-dependencies>
<directories>
<directory>cross_cutting/caching</directory>
<directory>cross_cutting/error_handling</directory>
<directory>cross_cutting/security</directory>
<directory>cross_cutting/telemetry</directory>
<directory>cross_cutting/validation</directory>
<directory>cross_cutting/workflows</directory>
</directories>
</layer>
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.
- 4d ago First seen · 273 lines · 0 tokens per session scan A 7161322b2faa
1002-python-clean-architecture is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,091 tokens. 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.
Other cursor rules, from other repositories
wrapup
End-of-session wrap-up: summarizes the session and pushes a log to the project's linked NotebookLM notebook. Activate with @wrapup in chat, or "wrap up", "save this session", or "end of session".
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
composer-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.
composer-debugging
Root-cause debugging — reproduce, trace data flow, test cheapest hypothesis, fix the cause not the symptom.