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 j4flmao/agent-skills --skill grpc-patternsgit clone --depth 1 https://github.com/j4flmao/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/j4flmao/agent-skills/grpc-patterns)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/grpc-patterns"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/grpc-patterns/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/j4flmao/agent-skills/grpc-patterns"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/grpc-patterns.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00132 | $0.04826 |
| Opus 5 | $0.00066 | $0.02413 |
| Sonnet 5 | $0.00026 | $0.00965 |
| Haiku 4.5 | $0.00013 | $0.00483 |
Grade A, and why
backend-grpc-patterns 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 8d 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 — 546 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend gRPC Patterns
Purpose
Design consistent, production-grade gRPC services. Every RPC must follow the same conventions for protobuf schemas, streaming patterns, interceptors, error handling, and service versioning.
Agent Protocol
Trigger
Exact user phrases: "gRPC", "protobuf", "protocol buffers", "streaming RPC", "unary call", "server streaming", "client streaming", "bidirectional streaming", "gRPC interceptor", "gRPC error handling", "protobuf schema", "service definition", "design an RPC", "gRPC contract".
Input Context
Before activating, verify:
- The service or feature being designed is known.
- The proto package name and version are known.
- The streaming model (unary/server-stream/client-stream/bidi) is chosen. If not, ask: "What streaming model do you need?"
- The language/runtime for code generation is known.
Output Artifact
No file output unless the user requests it. Produces protobuf schema and RPC specifications as text.
Response Format
For each RPC:
rpc {MethodName}({RequestType}) returns ({ResponseType})
Streaming: {none/server/client/bidirectional}
Auth: {required/optional/none}
Deadline: {timeout suggestion}
Errors: {list of gRPC status codes}
For a full service definition:
service {ServiceName} {
{list of RPCs}
}
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- All protobuf packages follow the naming conventions below.
- Every RPC has: method signature, streaming type, auth requirement, deadline, error codes.
- Protobuf messages are versioned in the package name.
- Error responses use standard gRPC status codes with rich detail.
- All streaming RPCs include proper backpressure handling.
- Interceptor chain is documented.
Max Response Length
Per RPC: 6 lines. Per service: unlimited.
Decision Tree
Which RPC Pattern?
What is the communication pattern?
├── Request → Response (standard CRUD)
│ └── Unary RPC — simplest, HTTP/2 under the hood
├── Request → stream of events (subscribe, watch, notifications)
│ └── Server-streaming RPC — send multiple responses for one request
├── Stream of requests → single response (batch upload, long-form input)
│ └── Client-streaming RPC — aggregate client data into one result
├── Stream → stream (chat, real-time sync, gaming)
│ └── Bidirectional streaming — full-duplex communication
└── Fire-and-forget (event, notification, pub/sub)
└── Consider message queue instead — gRPC streaming is for persistent connections
What ships with it
10 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.
- references/advanced_protobuf_schemas.md 13 KB
- references/grpc_interceptors.md 23 KB
- references/grpc-error-handling.md 8.9 KB
- references/grpc-interceptors.md 4.3 KB
- references/grpc-performance.md 7.6 KB
- references/grpc-security.md 8.0 KB
- references/grpc-streaming.md 3.9 KB
- references/grpc-testing.md 7.9 KB
- references/grpc-vs-rest.md 2.1 KB
- references/protobuf-basics.md 3.5 KB
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.
- 8d ago First seen · 546 lines · 132 tokens per session scan A 4693318c6f73
backend-grpc-patterns is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 5d ago), licensed MIT. It adds 132 tokens to every session and 4,826 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
hunt-grpc
Hunt gRPC vulnerabilities — server reflection enabled (enumerate all services/methods), missing authentication / metadata-stripping on internal endpoints, plaintext gRPC over HTTP/2, internal endpoint disclosure, proto file leakage, gRPC-Web/grpc-gateway transcoding injection, and HTTP/2 Rapid Reset DoS…
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
grpc-expert
Expert-level gRPC, Protocol Buffers, microservices communication, and streaming. Use when the user mentions Protocol Buffers, microservices, RPC, or streaming, or when the task involves gRPC Fundamentals, Communication Patterns, or Production Features.
opentelemetry
OpenTelemetry observability patterns: traces, metrics, logs, context propagation, OTLP export, Collector pipelines, and troubleshooting.
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
api-designer
Designs production-grade APIs — REST, GraphQL, gRPC, and AsyncAPI patterns including pagination, versioning, error handling, rate limiting, and API governance. Use when the user asks to design APIs, create endpoints, build an API layer, write OpenAPI specs, or needs help with REST/GraphQL/gRPC service design.