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 mohitmishra786/low-level-dev-skills --skill rdma-verbsgit clone --depth 1 https://github.com/mohitmishra786/low-level-dev-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/mohitmishra786/low-level-dev-skills/rdma-verbs)<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/rdma-verbs"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/rdma-verbs/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/mohitmishra786/low-level-dev-skills/rdma-verbs"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/rdma-verbs.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 | $0.00080 | $0.02057 |
| Opus 5 | $0.00040 | $0.01028 |
| Sonnet 5 | $0.00016 | $0.00411 |
| Haiku 4.5 | $0.00008 | $0.00206 |
Grade A, and why
rdma-verbs 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RDMA Verbs
Purpose
Guide agents through RDMA programming with libibverbs: one-sided vs two-sided operations, RC/UC/UD transports, device setup (ibv_get_device_list, protection domains, memory registration, completion queues, queue pairs), work requests and completions, RoCE vs InfiniBand, perftest benchmarking, and Rust rdma-sys bindings.
When to Use
- Building ultra-low-latency storage or database networking
- Bypassing CPU for remote memory access (one-sided RDMA)
- Setting up RoCE on Ethernet fabrics
- Benchmarking network fabric with perftest tools
- Integrating RDMA into MPI or custom RPC systems
- Debugging RDMA connection and completion errors
Workflow
1. RDMA concepts
RDMA stack
├── Application (libibverbs)
├── Kernel RDMA driver (mlx5, rdma_rxe)
├── NIC/HCA hardware
└── Fabric (InfiniBand or RoCE/Ethernet)
Operation types
├── Two-sided: Send/Recv (both sides participate)
└── One-sided: RDMA Read/Write (remote CPU not involved)
Transports:
| Type | Reliable | Connection | Use |
|---|---|---|---|
| RC (Reliable Connected) | Yes | 1:1 QP pair | General purpose |
| UC (Unreliable Connected) | No | 1:1 | Multicast-like |
| UD (Unreliable Datagram) | No | Many:Many | MPI, discovery |
2. Device discovery
# List RDMA devices
ibv_devices
ibv_devinfo
# RoCE link status
rdma link show
ibstat
# Perftest prerequisites
modprobe ib_umad
3. Minimal libibverbs setup
#include <infiniband/verbs.h>
#include <stdio.h>
#include <stdlib.h>
int main(void) {
int num_devices;
struct ibv_device **dev_list = ibv_get_device_list(&num_devices);
if (!dev_list || num_devices == 0) {
fprintf(stderr, "No RDMA devices\n");
return 1;
}
struct ibv_context *ctx = ibv_open_device(dev_list[0]);
struct ibv_pd *pd = ibv_alloc_pd(ctx);
char buf[4096];
struct ibv_mr *mr = ibv_reg_mr(pd, buf, sizeof(buf),
IBV_ACCESS_LOCAL_WRITE | IBV_ACCESS_REMOTE_WRITE);
struct ibv_cq *cq = ibv_create_cq(ctx, 10, NULL, NULL, 0);
struct ibv_qp_init_attr qp_attr = {
.send_cq = cq,
.recv_cq = cq,
.cap = { .max_send_wr = 10, .max_recv_wr = 10,
.max_send_sge = 1, .max_recv_sge = 1 },
.qp_type = IBV_QPT_RC,
};
struct ibv_qp *qp = ibv_create_qp(pd, &qp_attr);
printf("QP num %u, MR lkey %u rkey %u\n",
qp->qp_num, mr->lkey, mr->rkey);
ibv_destroy_qp(qp);
ibv_dereg_mr(mr);
ibv_destroy_cq(cq);
ibv_dealloc_pd(pd);
ibv_close_device(ctx);
ibv_free_device_list(dev_list);
return 0;
}
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 · 239 lines · 80 tokens per session scan A b9c9b04a22d5
rdma-verbs is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (203 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 2,057 once invoked, about $0.0004 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
gemini-api-agent-platform
Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
server-inference
Use this skill when the user wants to run or debug MLX-VLM server inference, including uv run mlxvlm.server, /v1/models, /v1/chat/completions, /v1/responses, streaming, OpenAI-compatible clients, health checks, metrics, model unload/reload, adapters, trust-remote-code, and server request/response failures.
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
ai-sdk
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…
ai-model-nodejs
Use this skill for Node.js backend AI via @cloudbase/node-sdk (>=3.16.0) — cloud functions, CloudRun, Express/Koa/NestJS, serverless APIs, scheduled jobs, LLM proxies, agent orchestration. The only SDK supporting image generation (ai.createImageModel + generateImage). Text via ai.createModel with groups cloudbase…