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 hamzabellouch/agent-skills --skill grpc-protobuf-microservicesgit clone --depth 1 https://github.com/hamzabellouch/agent-skillsWrote 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/hamzabellouch/agent-skills/grpc-protobuf-microservices)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/grpc-protobuf-microservices"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/grpc-protobuf-microservices/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/hamzabellouch/agent-skills/grpc-protobuf-microservices"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/grpc-protobuf-microservices.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 | $0.00040 | $0.01936 |
| Opus 5 | $0.00020 | $0.00968 |
| Sonnet 5 | $0.00008 | $0.00387 |
| Haiku 4.5 | $0.00004 | $0.00194 |
Grade A, and why
grpc-protobuf-microservices 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 12d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gRPC & Protocol Buffers Microservices Architecture
Overview
This skill provides production-grade standards for designing, implementing, and deploying high-performance microservices using gRPC and Protocol Buffers (proto3). It covers backward-compatible .proto schema evolution, unary and streaming RPC patterns, context deadline propagation, interceptor chains (middleware), and load balancing with Envoy.
1. Proto3 Schema & gRPC Core Principles
- Strict Backward Compatibility: Never alter existing field tags (numbers). Never change field types. Use
reservedstatements when deleting fields to prevent tag reuse. - Explicit Deadlines & Timeouts: Every gRPC client call must specify an explicit context deadline to prevent cascading hangs across microservices.
- Structured Error Handling: Use
google.rpc.Statuswith rich error details (BadRequest,PreconditionFailure,ResourceInfo) rather than simple gRPC status codes. - Streaming Semantics:
- Unary: Standard Request/Response pattern.
- Server Streaming: Continuous feed (e.g., real-time audit logs, telemetry).
- Client Streaming: Large file or batch data ingestion.
- Bi-directional Streaming: Low-latency interactive chat or real-time state synchronization.
- Transport Security (mTLS): Enforce mutual TLS authentication between internal microservices.
2. Microservice Communication Architecture
[ Client / Web App ]
│ HTTP/2 or gRPC-Web
▼
[ Envoy Reverse Proxy ] ──(gRPC Transcoding / Load Balancing)
│ gRPC over HTTP/2 (mTLS)
├──▶ [ Order Service (gRPC Server) ]
└──▶ [ Inventory Service (gRPC Server) ]
| RPC Pattern | Protocol Transport | Primary Use Case | Recommended Timeout |
|---|---|---|---|
| Unary RPC | HTTP/2 Single Frame | Transactional CRUD Operations | 500ms - 2s |
| Server Streaming | HTTP/2 Multi-Frame | Telemetry, Event Push, Activity Feeds | 15m - 1h (with keepalive) |
| Client Streaming | HTTP/2 Multi-Frame | Chunked File Upload, Batch Log Ingestion | 30s - 5m |
| Bi-directional | HTTP/2 Multiplexed | Live Synchronization, Streaming AI Inference | Continuous |
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.
- 12d ago First seen · 239 lines · 40 tokens per session scan A 075c7112e3f1
grpc-protobuf-microservices is a skill published in the GitHub repository hamzabellouch/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,936 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
api-and-interface-design
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
ubiquitous-language
Maintain a project thesaurus (domain glossary) following DDD ubiquitous language principles. Use PROACTIVELY when naming anything: variables, functions, classes, modules, database fields, API endpoints, events, files, or directories. Also use when the user asks to "create thesaurus", "update glossary", "add term"…
laravel-expert
Laravel & PHP Development Instructions for GitHub Copilot.
nodejs-codestyle
Custom Instructions: Node.js Backend & Architecture Expert.
php-laravel-codestyle
Custom Instructions: PHP 8+ & Laravel Architecture Expert.
api-design
Design and implement REST APIs with consistent conventions, versioning, error contracts, and security.