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 search-workflowgit 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/search-workflow)<a href="https://agentmods.dev/skills/mindspore-ai/akg/search-workflow"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/search-workflow/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/search-workflow"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/search-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 28 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00034 | $0.01006 |
| Opus 5 | $0.00017 | $0.00503 |
| Sonnet 5 | $0.00007 | $0.00201 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
search-workflow 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
搜索式算子生成（adaptive_search / evolve）
What I do
通过 adaptive_search 或 evolve 搜索式 workflow 生成高性能算子代码。以 silent mode 后台执行，轮询监控进度。
When to use me
主 Agent 的 Phase 3 中用户选择了 adaptive_search 或 evolve 时使用。
Workflow
1. 启动
使用命令模板后台启动 @scripts/run_workflow.py，输出重定向到 run.log：
<命令模板: nohup python @scripts/run_workflow.py 的绝对路径 \
--workflow <adaptive_search|evolve> \
--task-file /abs/path/{op_name}.py \
--framework <framework> --backend <backend> \
--arch <arch> --dsl <dsl> \
--output-path <output-path> \
> <output-path>/run.log 2>&1 & echo $!>
记录返回的 PID。
2. 轮询监控
每隔 ~1 分钟执行：
kill -0 <PID> 2>/dev/null && echo "RUNNING" || echo "FINISHED"
tail -n 10 <output-path>/run.log
RUNNING→ 继续轮询（间隔 1 分钟）FINISHED→ 进入结果收集
禁止擅自终止工作流
3. 结果收集
summary.json存在 → 读取success字段generated_code.py存在 → 成功- 均不存在 → 查看
run.log末尾获取错误信息
4. 中断控制（用户要求时）
kill <PID>
中断后按「部分结果恢复」处理。
部分结果恢复
adaptive_search / evolve 每完成一次成功验证就会写入 <output-path>/logs/。进程被杀时已写入的文件仍在。
核心原则：只要有 passed case 就不算失败。
<output-path>/logs/
├── passed_cases/{op_name}/ # 通过验证的迭代
│ └── Iteration{id}_Step{NN}_verify/
│ └── {op_name}_{dsl}_impl.py # 实现代码
├── {op_name}/profiling/
│ └── speed_up_record.txt # 加速比记录
└── verification_results.jsonl
恢复步骤：
- 检查
logs/passed_cases/{op_name}/是否有内容 - 读取
speed_up_record.txt，找性能最佳记录对应的unique_dir - 从
passed_cases/{op_name}/{unique_dir}/读取实现代码 - 写入
<output-path>/generated_code.py
Workflow 参数
| workflow | 特点 | 典型耗时 |
|---|---|---|
adaptive_search |
UCB 策略、即时递补、收敛快 | 10-30 分钟 |
evolve |
岛屿模型、多样性强 | 15-60 分钟 |
adaptive_search 特定参数:
--max-concurrent（默认 2）、--initial-tasks（默认 2）、--max-tasks（默认 10）
evolve 特定参数:
--max-rounds（默认 3）、--parallel-num（默认 4）、--num-islands（默认 2）
方式 B: akg_cli 调用（替代方案）
仅当需要 --resume 恢复会话或 --worker_url 远程 Worker 时使用：
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 · 120 lines · 34 tokens per session scan A 1d3c82a8aa60
search-workflow is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,006 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 2026-09-03.
Other skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
minicpm5-deploy-vllm-ascend
Deploy MiniCPM5-2B with vLLM on Huawei Ascend NPU using vLLM-Ascend. Use when the user mentions vLLM-Ascend, Ascend NPU, Huawei Ascend, CANN, torchnpu, davinci devices, or wants an OpenAI-compatible MiniCPM5 server on Ascend hardware.
minicpm5-deploy-litert
Run MiniCPM5-2B or MiniCPM5-1B on-device with Google's LiteRT-LM runtime — the litert-lm CLI or its OpenAI-compatible server on a desktop, the Kotlin API or the AI Edge Gallery app on Android, the same .litertlm bundle on CPU or GPU. Use when the user says "LiteRT", "LiteRT-LM", "litertlm", ".litertlm", "Android"…