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 AMD-AGI/Apex --skill mi300-hip-vs-nvidiagit clone --depth 1 https://github.com/AMD-AGI/ApexWrote 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/amd-agi/apex/mi300-hip-vs-nvidia)<a href="https://agentmods.dev/skills/amd-agi/apex/mi300-hip-vs-nvidia"><img src="https://agentmods.dev/badge/skills/amd-agi/apex/mi300-hip-vs-nvidia/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/amd-agi/apex/mi300-hip-vs-nvidia"><img src="https://agentmods.dev/badge/skills/amd-agi/apex/mi300-hip-vs-nvidia.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 | $0.00035 | $0.00285 |
| Opus 5 | $0.00017 | $0.00143 |
| Sonnet 5 | $0.00007 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
mi300-hip-vs-nvidia 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.
What it actually says
MI300 vs NVIDIA (HIP Porting Guide)
Use when porting/tuning kernels from NVIDIA to MI300 or comparing behaviors.
Key differences and guidance:
- Execution: 64-thread wavefronts vs 32-thread warps—adjust coalescing, tails, and occupancy; watch register/LDS pressure per wavefront.
- Memory: CDNA3 cache hierarchy and vector cache; coalesce for 64 threads; exploit LDS; understand cache line sizes/policies.
- Matrix cores: MFMA set, mixed precision; adapt tiling/layout for Matrix Cores; leverage scalar unit for uniform ops.
- Synchronization/atomics: wave-level sync, memory ordering; extra fences for relaxed coherency; cooperative groups considerations.
- Compiler/feature guards: use HIP macros and arch detection; conditional MFMA paths.
- Optimization: occupancy sizing (multiples of 64), instruction scheduling, mixed precision, load balancing across shader engines, fusion when resources allow.
- Profiling/debug: use ROCProfiler/ROCgdb for wavefront-aware analysis; check launch config impacts on occupancy/memory.
References:
references/HIP Kernel Programming Guide for MI300_ Key Differences from NVIDIA AI Chips.md
What ships with it
1 file 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.
- 9d ago First seen · 21 lines · 35 tokens per session scan A 9e3b26ad07d1
mi300-hip-vs-nvidia is a skill published in the GitHub repository AMD-AGI/Apex (76 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 285 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 2026-08-30.
Other skills, from other repositories
optimize-global-memory-access
Guide the agent through diagnosing and restructuring CUDA global memory access patterns to maximize effective memory bandwidth, covering coalescing requirements, vectorized loads, AoS vs SoA layouts, shared memory staging for non-coalesced patterns, and L2 cache behavior.
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…
doca-argp
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring docaargpinit → register params → docaargpstart → docaargpdestroy in order; picking a parameter type from the full public enum (DOCAARGPTYPESTRING, INT, BOOLEAN, DEVICE, DEVICEREP…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
zener-language
Read or edit Zener HDL, package APIs, and tool-managed dependencies.
embedded-stm32
Best practices for embedded C/C++ development on STM32 microcontrollers using the HAL, covering peripherals, DMA, interrupts, memory constraints, and hardware-focused testing. Use when writing STM32 HAL code, configuring peripherals generated by STM32CubeMX, working with interrupts or DMA, debugging with SWD/JTAG…