agentmods.dev

kernel-KBS

A searchable, source-backed collection of GPU kernel research for CUDA, Triton, CuTe, CUTLASS, and NVIDIA Ampere, Hopper, and Blackwell GPUs. It includes implementation history and related technical notes.

In plain words
What is it for?
Use it to find merged kernel pull requests, inspect code changes and their origins, read KernelWiki summaries, and retrieve supporting notes for GPU research.
Why use it?
It reduces the time spent searching scattered pull requests, documentation, blogs, and contest material for evidence about GPU implementations.

Skill for Claude CodeCodex

14 3mo ago A scan 109 tokens no licence
View the source file fmh66/kernel-opt-agent
Install

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.

agentmods
npx agentmods add skills/fmh66/kernel-opt-agent/kernel-kbs
Any agent
npx skills add fmh66/kernel-opt-agent --skill kernel-kbs
Clone the repo
git clone --depth 1 https://github.com/fmh66/kernel-opt-agent

Made for: Claude Code, Codex.

Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,507 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00109 $0.01507
Opus 5 $0.00055 $0.00754
Sonnet 5 $0.00022 $0.00301
Haiku 4.5 $0.00011 $0.00151

Measured 2d ago against content hash acd4f1307541, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kernel-KBS 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 2d ago.

The scan reads SKILL.md. This mod also ships 15 executable files (scripts/_wiki_root.py, scripts/collect_contest_code.py, scripts/compute_core_prs.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/kernel-KBS/SKILL.md · 142 lines

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.

Read it on GitHub

Files

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.

Changes

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.

  1. 2d ago First seen · 142 lines · 109 tokens per session scan A acd4f1307541

Subscribe to this mod's changes

kernel-KBS is a skill published in the GitHub repository fmh66/kernel-opt-agent (14 stars, last pushed 3mo ago), with no licence file. It adds 109 tokens to every session and 1,507 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 2026-08-30.

Memory and contextResearchWriting and docsagentaiinfracudacute-dslskillstriton
Related

Other skills, from other repositories

mlir-opt-skill

Use when optimizing MLIR GPU performance, compiling PyTorch or linalg/tensor MLIR to PTX, writing Transform dialect schedules, tuning auxiliary pass pipelines, benchmarking MLIR kernels against PyTorch, or diagnosing linalg/torch-mlir GPU codegen.

fmh66/MLIR-OPT-SKILL · 59 tokens

dingtalk_channel_connect

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.

agentscope-ai/QwenPaw · 69 tokens

pdf

当用户需要对PDF文件进行任何操作时，请使用此技能。包括从 PDF 中读取或提取文本/表格、合并多个 PDF、拆分 PDF、旋转页面、添加水印、创建新PDF、填写PDF表单、加密/解密 PDF、提取图片，以及对扫描版 PDF 进行 OCR 使其可搜索。如果用户提到 .pdf 文件或要求生成 PDF，请使用此技能。.

agentscope-ai/QwenPaw · 95 tokens

make_plan

For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.

agentscope-ai/QwenPaw · 51 tokens

gpt-image-2

面向 GPT Image 2 的图像生成 / 编辑技能。可在 3 种环境下使用：(A) Garden 本地模式，通过 OpenAI 兼容接口直接出图并落盘；(B) Host-Native 模式，把本 Skill 当作提示词工程指引，把渲染好的 prompt 交给宿主 Agent 自带的图像工具出图；(C) Advisor 模式，宿主无任何图像工具时退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板，覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。.

ConardLi/garden-skills · 177 tokens

new

Create a new project to start development quickly.

clacky-ai/openclacky · 10 tokens