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 mindspore-ai/akg --skill coder-agentgit clone --depth 1 https://github.com/mindspore-ai/akgWrote 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/mindspore-ai/akg/coder-agent)<a href="https://agentmods.dev/skills/mindspore-ai/akg/coder-agent"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/coder-agent/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/mindspore-ai/akg/coder-agent"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/coder-agent.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 | $0.00016 | $0.02076 |
| Opus 5.5 | $0.00006 | $0.00830 |
| Sonnet 5.5 | $0.00003 | $0.00415 |
| Haiku 4.5 | $0.00002 | $0.00208 |
Grade A, and why
coder-agent 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 1mo 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coder Agent - 代码生成专家
角色定位
Coder Agent是 AKG Agents 中的核心代码生成组件,负责:
- 将算法设计转换为高性能代码
- 支持多种DSL(CUDA、Triton、OpenCL等)
- 支持多种硬件后端(NVIDIA、AMD、Intel等)
- 提供代码优化建议
核心能力
1. 多DSL支持
CUDA
- 完整的CUDA C++语法
- Kernel launch配置优化
- 内存管理(global, shared, register)
- 性能优化技巧
Triton
- Python-like语法
- 自动内存管理
- Block-level编程
- 编译器优化
OpenCL
- 跨平台支持
- 标准内核语法
- 平台特定优化
2. 多后端支持
| 后端 | 架构 | DSL优先级 |
|---|---|---|
| NVIDIA GPU | CUDA | CUDA > Triton > OpenCL |
| AMD GPU | ROCm | OpenCL > HIP |
| Intel GPU | OneAPI | SYCL > OpenCL |
3. 代码优化
内存优化
- 合并内存访问(Coalesced Access)
- 减少Bank Conflict
- 使用Shared Memory缓存
- Prefetching技术
计算优化
- 循环展开(Loop Unrolling)
- 指令级并行(ILP)
- Warp级优化
- Tensor Core利用
配置优化
- Block size调优
- Grid size计算
- Occupancy最大化
- Register压力控制
工作流程
输入: 算法设计 + 目标后端 + 性能要求
↓
步骤1: 加载相关Skill(如cuda-basics, triton-syntax)
↓
步骤2: 生成初始代码框架
↓
步骤3: 填充计算逻辑
↓
步骤4: 应用优化技巧
↓
步骤5: 添加错误处理
↓
输出: 可编译的高性能代码
代码生成策略
保守策略(Conservative)
- 优先正确性
- 使用标准模式
- 适合初次实现
迭代策略(Iterative)
- 先简单实现
- 逐步优化
- 适合复杂算子
激进策略(Aggressive)
- 直接使用高级优化
- 可能需要调试
- 适合性能关键场景
代码模板
CUDA MatMul模板
__global__ void matmul_kernel(
const float* A,
const float* B,
float* C,
int M, int N, int K
) {
// 共享内存
__shared__ float As[TILE_SIZE][TILE_SIZE];
__shared__ float Bs[TILE_SIZE][TILE_SIZE];
// 计算线程索引
int row = blockIdx.y * TILE_SIZE + threadIdx.y;
int col = blockIdx.x * TILE_SIZE + threadIdx.x;
float sum = 0.0f;
// 分块计算
for (int tile = 0; tile < (K + TILE_SIZE - 1) / TILE_SIZE; ++tile) {
// 加载数据到共享内存
if (row < M && (tile * TILE_SIZE + threadIdx.x) < K)
As[threadIdx.y][threadIdx.x] = A[row * K + tile * TILE_SIZE + threadIdx.x];
else
As[threadIdx.y][threadIdx.x] = 0.0f;
if (col < N && (tile * TILE_SIZE + threadIdx.y) < K)
Bs[threadIdx.y][threadIdx.x] = B[(tile * TILE_SIZE + threadIdx.y) * N + col];
else
Bs[threadIdx.y][threadIdx.x] = 0.0f;
__syncthreads();
// 计算部分和
#pragma unroll
for (int k = 0; k < TILE_SIZE; ++k) {
sum += As[threadIdx.y][k] * Bs[k][threadIdx.x];
}
__syncthreads();
}
// 写回结果
if (row < M && col < N) {
C[row * N + col] = sum;
}
}
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.
- 1mo ago First seen · 283 lines · 16 tokens per session scan A 1e23fce7f1e9
coder-agent is a skill published in the GitHub repository mindspore-ai/akg (263 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 2,076 once invoked, about $0.0001 per session on Opus 5.5. 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
profinet
PROFINET (L2 EtherType 0x8892 / DCP) attack playbook — DCP Identify-All broadcast enumeration, device fingerprinting, station-name and IP reassignment (breaks IO-controller mapping), flash-LED physical location, factory-reset, RT frame injection/replay for cyclic-IO spoofing. Siemens/EU fieldbus peer of S7Comm…
opentrons-integration
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
pylabrobot
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API…
ics-overview
Use when the target is an industrial control system or operational technology network running Modbus, BACnet, S7Comm/S7Comm Plus, DNP3, OPC-UA, or any PLC/HMI/SCADA stack. Engagements MUST set RoE flag industrialsafetycritical=true; this catalog gates every write-scope operation behind explicit operator confirmation…
omh-physical-device-readiness
This is an OMH physical-device-readiness workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
x-smart
SMART disk health monitoring tool. Check disk health, temperature, and attributes using smartctl. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.