Borrowing it
Nothing to install: this file belongs to rafaelghif/antigravity-agents. 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/rafaelghif/antigravity-agents/main/.agents/skills/architecture/SKILL.mdgit clone --depth 1 https://github.com/rafaelghif/antigravity-agentsWrote 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/rafaelghif/antigravity-agents/architecture)<a href="https://agentmods.dev/skills/rafaelghif/antigravity-agents/architecture"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/architecture/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/rafaelghif/antigravity-agents/architecture"><img src="https://agentmods.dev/badge/skills/rafaelghif/antigravity-agents/architecture.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 | $0.00039 | $0.01060 |
| Opus 5 | $0.00019 | $0.00530 |
| Sonnet 5 | $0.00008 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distributed System Architecture & Resilience Protocol
Role: Principal Distributed Systems Architect & LLM Reliability Lead.
Overview & Trigger Conditions
Activate this skill when designing system architectures, defining or modifying public API contracts, implementing inter-service communication, structuring domain boundaries, or establishing distributed resilience patterns.
Trigger Scenarios & Keywords:
- System design, DDD restructuring, API contracts, controllers, services, repositories.
- Resilience patterns:
idempotency,circuit breaker,transactional outbox,retry backoff,deadlock. - API error handling: RFC 7807 problem details, DTO schemas, backward compatibility.
Core Architecture Standards
-
Domain-Driven Isolation & Layered Boundaries:
- Strictly adhere to established architectural patterns (Clean Architecture, Hexagonal, Modular Monolith).
- Unidirectional layering: Controller / Transport -> Domain Business Logic -> Repository / Infrastructure.
- Domain logic must never depend on transport frameworks (Express, FastAPI) or database ORM models directly.
- YAGNI: Speculative abstraction layers and generic wrappers without multiple callers are strictly forbidden.
-
API Contract Governance & Backward Compatibility:
- APIs are permanent public contracts. Field deletion or renaming without major version bumps is BANNED.
- Enums are append-only. All newly introduced request fields MUST be optional with safe default values.
- RFC 7807 Problem Details: HTTP error responses must return structured JSON (
type,title,status,detail,instance,code). Never leak raw database errors or stack traces. - Schema-First Validation: Validate all inbound payloads via strict DTO schemas (Zod, Pydantic, Protobuf) at the network boundary.
-
Distributed Resilience & Fault Tolerance:
- Idempotency Keys: All state-mutating endpoints require an
Idempotency-Keyheader with cached response re-delivery. - Full Jitter Exponential Backoff: Never use fixed sleep loops. Apply randomized exponential backoff: $$T_{\text{sleep}} = \text{random}(0, \min(T_{\text{max}}, T_{\text{base}} \times 2^{\text{attempt}}))$$
- Transactional Outbox Pattern: Dual writes to database and message broker are forbidden. Write domain events to an
outboxtable in the primary database transaction; dispatch via dedicated background relay or CDC. - Circuit Breakers: Wrap external network calls in circuit breakers (trip open upon >50% failure rate; serve graceful fallbacks).
- Deadlock Prevention: Acquire multi-entity locks in globally consistent sorted order. Prefer optimistic concurrency versioning (
version = version + 1).
- Idempotency Keys: All state-mutating endpoints require an
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.
- yesterday Changed 2bbf476b9773
- 2d ago Changed · +38 lines · +5 tokens per session f37ce55c1b08
- 4d ago Changed · +1 lines · +7 tokens per session 290051300318
- 9d ago First seen · 38 lines · 27 tokens per session scan A 39234df17dac
architecture is a skill published in the GitHub repository rafaelghif/antigravity-agents (5 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 1,060 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
cicd
Automated CI/CD pipeline scaffolding, multi-job quality gates, Dependabot smart auto-merge, and CD release workflows for projects in PARA workspace.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
ci-cd-and-automation
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
agentic-actions-auditor
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches. AI agents running in CI/CD pipelines.
godot-export
Export and build a Godot 4.7 project for distribution: install export templates, define export presets (Windows/macOS/Linux/Web/Android), run headless command-line exports for CI, and handle web (HTML5) COOP/COEP and dedicated-server/headless builds. Use when exporting a Godot game, configuring exportpresets.cfg…
nx-workspace-patterns
Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.