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 Fandhe-AI/agent-reference-skills --skill amd-rocmgit clone --depth 1 https://github.com/Fandhe-AI/agent-reference-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/fandhe-ai/agent-reference-skills/amd-rocm)<a href="https://agentmods.dev/skills/fandhe-ai/agent-reference-skills/amd-rocm"><img src="https://agentmods.dev/badge/skills/fandhe-ai/agent-reference-skills/amd-rocm/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/fandhe-ai/agent-reference-skills/amd-rocm"><img src="https://agentmods.dev/badge/skills/fandhe-ai/agent-reference-skills/amd-rocm.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 | $0.00091 | $0.01691 |
| Opus 5 | $0.00046 | $0.00846 |
| Sonnet 5 | $0.00018 | $0.00338 |
| Haiku 4.5 | $0.00009 | $0.00169 |
Grade A, and why
amd-rocm 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 9d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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/gpu-arch/cdna-architecture.md 3.4 KB
- references/gpu-arch/gpu-arch-specs.md 3.8 KB
- references/gpu-arch/gpu-architecture-overview.md 3.5 KB
- references/gpu-arch/isa-documentation.md 3.3 KB
- references/gpu-arch/machine-readable-isa.md 1.6 KB
- references/gpu-arch/mi100-microarchitecture.md 1.5 KB
- references/gpu-arch/mi250-microarchitecture.md 1.8 KB
- references/gpu-arch/mi300-mi200-performance-counters.md 2.1 KB
- references/gpu-arch/mi300-microarchitecture.md 1.7 KB
- references/gpu-arch/mi350-performance-counters.md 1.7 KB
- references/gpu-arch/performance-optimization-guides.md 3.7 KB
- references/gpu-arch/precision-support.md 2.3 KB
- references/gpu-arch/rdna-architecture.md 2.8 KB
- references/gpu-arch/README.md 2.0 KB
- references/hip/asynchronous-execution.md 1.8 KB
- references/hip/compilers-clr.md 1.7 KB
- references/hip/cooperative-groups.md 2.7 KB
- references/hip/cpp-language-extensions.md 2.2 KB
- references/hip/cuda-to-hip-api-comparison.md 1.7 KB
- references/hip/debugging-logging.md 1.5 KB
- references/hip/deprecated-apis.md 2.1 KB
- references/hip/device-management.md 2.4 KB
- references/hip/device-memory.md 2.1 KB
- references/hip/env-variables.md 1.9 KB
- references/hip/error-handling.md 1.7 KB
- references/hip/event-management.md 1.9 KB
- references/hip/execution-control-launch.md 2.3 KB
- references/hip/graph-management.md 2.4 KB
- references/hip/hardware-features.md 1.6 KB
- references/hip/hardware-implementation.md 1.5 KB
- references/hip/hipify.md 2.7 KB
- references/hip/hiprtc.md 2.6 KB
- references/hip/host-memory.md 2.0 KB
- references/hip/initialization-version.md 1.8 KB
- references/hip/interop.md 2.0 KB
- references/hip/kernel-language-cpp-support.md 1.9 KB
- references/hip/math-api.md 1.5 KB
- references/hip/memory-management.md 2.2 KB
- references/hip/module-context-management.md 2.4 KB
- references/hip/multi-device-peer-to-peer.md 1.9 KB
- references/hip/occupancy.md 1.5 KB
- references/hip/performance-guidelines.md 1.6 KB
- references/hip/porting-cuda-to-hip.md 1.8 KB
- references/hip/programming-model.md 2.3 KB
- references/hip/README.md 4.4 KB
- references/hip/runtime-api-overview.md 1.6 KB
- references/hip/stream-management.md 3.1 KB
- references/hip/stream-ordered-allocator.md 2.1 KB
- references/hip/texture-surface.md 2.0 KB
- references/hip/unified-memory.md 2.0 KB
- references/hip/virtual-memory.md 2.3 KB
- references/rocm-stack/ai-ecosystem.md 1.2 KB
- references/rocm-stack/communication-libraries.md 1.0 KB
- references/rocm-stack/compatibility-and-release-history.md 1.5 KB
- references/rocm-stack/control-monitoring-tools.md 1.1 KB
- references/rocm-stack/core-sdk-overview.md 1.4 KB
- references/rocm-stack/gpu-systems-infra.md 1.4 KB
- references/rocm-stack/install-deep-learning-frameworks.md 1.8 KB
- references/rocm-stack/install-docker-spack.md 1.7 KB
- references/rocm-stack/install-linux.md 1.9 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.
- 9d ago First seen · 153 lines · 91 tokens per session scan A 58b071cef184
amd-rocm is a skill published in the GitHub repository Fandhe-AI/agent-reference-skills (3 stars, last pushed today), with no licence file. It adds 91 tokens to every session and 1,691 once invoked, about $0.0005 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.