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-programming-insightsgit 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-programming-insights)<a href="https://agentmods.dev/skills/amd-agi/apex/mi300-hip-programming-insights"><img src="https://agentmods.dev/badge/skills/amd-agi/apex/mi300-hip-programming-insights.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00279 |
| Opus 5 | $0.00020 | $0.00139 |
| Sonnet 5 | $0.00008 | $0.00056 |
| Haiku 4.5 | $0.00004 | $0.00028 |
Grade A, and why
mi300-hip-programming-insights 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.
What it actually says
MI300 HIP Programming Insights
Use when tuning HIP kernels with CDNA3 architectural context (chiplets, caches, matrix cores).
Highlights:
- Memory hierarchy: 128B cache lines; leverage 256MB Infinity Cache (temporal locality); explicit sync across XCDs (relaxed coherency).
- Workgroups: size for 4 ACEs per XCD; balance across 38 CUs; exploit shared I-cache locality; LDS 64KB per CU.
- Matrix cores: align data; overlap matrix + vector + memory; choose FP8/TF32 for throughput vs precision; schedule for concurrency.
- Sparsity: 2:4 structured sparsity (INT8/FP8/FP16/BF16); weigh reordering overhead vs gains; good for attention/conv.
- Cross-platform: HIP differences vs CUDA—explicit fences, data-type fallbacks, platform-specific tuning.
- Debug/profiling: use ROCm tools to analyze cache misses, bandwidth, sync overhead; focus on memory-side cache behavior.
References:
references/AMD MI300 HIP Kernel Programming Guide_ CDNA3 Architecture Insights.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.
- 8d ago First seen · 20 lines · 41 tokens per session scan A a4e31ef3e73f
mi300-hip-programming-insights is a skill published in the GitHub repository AMD-AGI/Apex (76 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 279 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
choose-launch-configuration
Guide the agent through selecting the correct and efficient thread block dimensions and grid dimensions for a CUDA kernel, covering occupancy analysis, register and shared memory constraints, tail effects, persistent kernels, and when to use cudaOccupancyMaxActiveBlocksPerMultiprocessor as a decision tool.
write-backend-agnostic-kernel-plan
Guide the agent through planning a compute kernel that must run correctly and performantly on multiple hardware backends (NVIDIA, AMD, CPU fallback, or future backends) before any backend-specific implementation is written — covering abstraction strategy, feature compatibility mapping, and the tradeoffs between…
write-fp8-kernel
Guide the agent through designing and implementing FP8 compute kernels for inference and training on NVIDIA Hopper (sm90) and Ada Lovelace (sm89) hardware, covering FP8 format selection, scaling strategy, tensor core usage via WGMMA or cuBLAS, and dequantization epilogue design.
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.
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.