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 skills add joao-aires/agent-skills-public --skill backend-conventionsgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/backend-conventions)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/backend-conventions"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/backend-conventions/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/joao-aires/agent-skills-public/backend-conventions"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/backend-conventions.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 | $0.00063 | $0.02588 |
| Opus 5.5 | $0.00025 | $0.01035 |
| Sonnet 5.5 | $0.00013 | $0.00518 |
| Haiku 4.5 | $0.00006 | $0.00259 |
Grade A, and why
backend-conventions 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend conventions
Establish the system's shape
Read the request, AGENTS.md, architecture and existing code. Accept reference repositories, API examples, schemas, architecture decisions or platform constraints. Extract applicable boundaries and behaviors rather than copying an entire system. Preserve accepted choices; record meaningful deviations in existing architecture/project notes without requiring a new profile format.
For new services, prefer a supported Python, uv with a committed lockfile, FastAPI/Uvicorn, Pydantic v2 and settings, SQLAlchemy 2, Alembic, PostgreSQL, Ruff, pytest and HTTPX.
- Match installed APIs and dependency versions.
- Upstream tooling suggestions are defaults for compatible new projects, not permission to replace an existing type checker, hook runner, package manager or application layout.
- Use async end-to-end where suitable drivers and concurrency needs justify it; an intentional synchronous stack is valid.
- Do not run blocking I/O inside async handlers or mistake async/thread pools for a CPU scaling strategy.
| System type | Starting approach |
|---|---|
| Application API | One deployable service with clear domain boundaries; add services only for an actual independent responsibility. |
| Durable background work | Worker/queue when work must survive process loss; define status, retries, cancellation and recovery according to the task. |
| Event-driven integration | Idempotent consumers and explicit delivery assumptions; use an outbox when database changes and delivery intent must be atomic. Do not promise exactly-once delivery. |
| AI or MCP interface | Narrow authorized adapters over application services; introduce a framework only for capabilities the system needs. |
Apply the service contract
Use installed service-contract design expertise for actor authority, invariants, state/failure, transaction and consumer contracts before substantive implementation; seek architecture expertise when consequential boundaries need decisions. Discover optional guidance through the actual inventory rather than another plugin's path. Without it, establish the affected behavior, ownership, failure semantics and observable acceptance in existing notes before coding. A local fix needs no new design ceremony.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · +70 lines 3c2eaf541234
- 2d ago Changed · -2 lines 5132dbaba75f
- 3d ago Changed · -4 lines 166bfcf08cf2
- 7d ago Changed · +40 lines 65bc9f13fa1c
- 10d ago First seen · 67 lines · 63 tokens per session scan A f6f66c2ad59d
backend-conventions is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 2,588 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 2026-10-12.
Other skills, from other repositories
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
stripe-projects
Use after E2B sandbox/API access has been provisioned through Stripe Projects and the user needs to use the resulting E2B API key with the E2B CLI, JavaScript SDK, Python SDK, or Code Interpreter SDK.
azure-messaging-webpubsubservice-py
Azure Web PubSub Service SDK for Python. Use for real-time messaging, WebSocket connections, and pub/sub patterns. Triggers: "azure-messaging-webpubsubservice", "WebPubSubServiceClient", "real-time", "WebSocket", "pub/sub".
azure-mgmt-botservice-py
Azure Bot Service Management SDK for Python. Use for creating, managing, and configuring Azure Bot Service resources. Triggers: "azure-mgmt-botservice", "AzureBotService", "bot management", "conversational AI", "bot channels".
django-pro
Master Django 5.x with async views, DRF, Celery, and Django Channels. Build scalable web applications with proper architecture, testing, and deployment. Use PROACTIVELY for Django development, ORM optimization, or complex Django patterns.
fastapi-pro
Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROACTIVELY for FastAPI development, async optimization, or API architecture.