Anima is an open-source local-network runtime that gives household hardware an AI layer for sensing environments, remembering preferences, planning actions, and controlling devices through adapters. It is intended for intelligent devices such as lights, air conditioners, humidifiers, air purifiers, and speakers, with a dashboard, REST API, and CLI for control and extension. The catalogue entries are skills, rules, and instructions for working with Anima.
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/fullive-ai/anima/architecture-guardrailsgit clone --depth 1 https://github.com/Fullive-AI/AnimaWrote 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/fullive-ai/anima/architecture-guardrails)<a href="https://agentmods.dev/rules/fullive-ai/anima/architecture-guardrails"><img src="https://agentmods.dev/badge/rules/fullive-ai/anima/architecture-guardrails.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 5.1 | $0.00326 | $0.00326 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
Architecture-Guardrails 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 6d 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.
What it actually says
Protect the existing architecture unless the task explicitly requires architectural change.
Core principles
- Prefer local, minimal, boundary-respecting changes.
- Fit new work into existing module boundaries whenever possible.
- Do not introduce new layers, abstractions, or patterns unless clearly justified.
- Do not widen the change surface unnecessarily.
- Do not use a bug fix or small feature as an excuse for broad redesign.
Before changing code
First identify:
- the owning module or subsystem
- its direct dependencies
- the inbound callers or consumers
- the outward contracts it exposes
- whether the change belongs here or elsewhere
Guardrails
- Keep responsibilities separated.
- Respect dependency direction.
- Do not move logic across layers without a strong reason.
- Avoid creating duplicate sources of truth.
- Prefer extending an existing abstraction over inventing a parallel one.
- Prefer explicit data flow over hidden coupling.
- Keep cross-module changes small and intentional.
Prohibited behavior unless clearly necessary
- broad refactors unrelated to the task
- introducing framework-level patterns for small local problems
- changing multiple subsystems to support a narrow fix when a local fix is possible
- creating generic helpers too early
- mixing transport, domain, UI, persistence, and integration logic in the same place
If architectural change is genuinely required
Then:
- State why the existing structure blocks the task.
- Keep the change as small as possible.
- Preserve backward compatibility where feasible.
- Update tests and docs affected by the architectural shift.
- Avoid combining architectural cleanup with unrelated feature work.
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.
- 6d ago First seen · 52 lines · 326 tokens per session scan A b2eb215bb00c
Architecture-Guardrails is a cursor rule published in the GitHub repository Fullive-AI/Anima (1,049 stars, last pushed 16d ago), licensed Apache-2.0. It adds 326 tokens to every session, about $0.0016 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 cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.