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 agentmods add skills/alibaba/anolisa/kernel-devnpx skills add alibaba/anolisa --skill kernel-devgit clone --depth 1 https://github.com/alibaba/anolisaWhat 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 | $0.00112 | $0.04926 |
| Opus 5 | $0.00056 | $0.02463 |
| Sonnet 5 | $0.00022 | $0.00985 |
| Haiku 4.5 | $0.00011 | $0.00493 |
Grade B, and why
kernel-dev scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo yum install -y \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
git ccache dwarves wget curl kmod \ How it starts
The opening of the file, as written. The whole thing — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kernel Development - Linux 内核研发自动化
核心定位
五大功能:
- 依赖检测与安装 - 自动检测并安装内核开发所需的软件包
- 工具链安装 - 安装编译器(gcc)、make、git 等开发工具
- 内核 devel 包安装 - 下载并安装当前系统内核的 devel 包
- 内核编译 - 支持两种编译方法:
- SRPM 方法:Alinux4 官方内核,输出 RPM 包,适合生产环境
- Upstream 方法:kernel.org 最新内核,编译快速,适合新特性测试
- Module 编译测试 - 测试编译示例内核 module
支持架构:
x86_64— Intel/AMD 64 位服务器aarch64— ARM 64 位服务器(如倚天 710)
重要约束:
- 🔒 需要 root 权限执行内核相关操作
- 📦 仅Linux操作系统
- ⚠️ 内核编译会消耗大量系统资源(建议至少 4GB 内存)
- ⏱️ 编译时间:SRPM 方法 1-3 小时,Upstream 方法 30-60 分钟
快速开始
一键搭建开发环境
# 1. 检测系统架构
ARCH=$(uname -m)
KERNEL_VER=$(uname -r)
echo "架构: $ARCH | 内核: $KERNEL_VER"
# x86_64 示例输出:架构: x86_64 | 内核: 6.6.102-5.2.alnx4.x86_64
# aarch64 示例输出:架构: aarch64 | 内核: 6.6.102-5.2.alnx4.aarch64
# 2. 检查 Alinux4 系统
grep -i 'alinux\|alnx' /etc/os-release || echo "[警告] 非 Alinux4 系统"
# 3. 安装所有依赖(两种架构通用)
sudo yum install -y \
gcc gcc-c++ make binutils \
flex bison \
libelf-devel openssl-devel ncurses-devel \
pahole perl python3 python3-devel \
git ccache dwarves wget curl kmod \
rpm-build rpmdevtools
# 4. 安装内核 devel 包(yum 自动匹配当前架构)
sudo yum install -y kernel-devel-$KERNEL_VER kernel-headers-$KERNEL_VER
# 5. 验证环境
ls -l /lib/modules/$KERNEL_VER/build
gcc --version
# 6. 编译内核(可选,两种方法)
# 方法 A: Upstream 方法(推荐,快速)
sudo ./scripts/build-kernel.sh upstream latest 8 defconfig
# 方法 B: SRPM 方法(Alinux4 官方)
sudo ./scripts/build-kernel.sh srpm 6.6.102-5.2.alnx4.x86_64
创建第一个内核模块
MODULE_NAME="hello_module"
mkdir -p $MODULE_NAME && cd $MODULE_NAME
# 创建模块代码
cat > ${MODULE_NAME}.c << 'EOF'
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Alinux4 Kernel Dev");
MODULE_DESCRIPTION("Hello World kernel module for alnx4");
MODULE_VERSION("0.1");
static int __init hello_init(void)
{
printk(KERN_INFO "hello_module: Module loaded (alnx4)\n");
return 0;
}
static void __exit hello_exit(void)
{
printk(KERN_INFO "hello_module: Module unloaded\n");
}
module_init(hello_init);
module_exit(hello_exit);
EOF
# 创建 Makefile
cat > Makefile << 'EOF'
obj-m += hello_module.o
KERNEL_DIR := /lib/modules/$(shell uname -r)/build
PWD := $(shell pwd)
all:
make -C $(KERNEL_DIR) M=$(PWD) modules
clean:
make -C $(KERNEL_DIR) M=$(PWD) clean
install:
sudo insmod hello_module.ko
unload:
sudo rmmod hello_module
.PHONY: all clean install unload
EOF
# 编译和加载
make
sudo make install
# 查看日志
dmesg | tail
# 卸载
sudo make unload
What ships with it
23 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.
- docs/build-performance.md 5.4 KB
- docs/module-signing.md 4.1 KB
- docs/troubleshooting.md 5.4 KB
- examples/build-kernel.md 8.0 KB
- examples/build-module.md 1.5 KB
- examples/char_device/char_device.c 4.6 KB
- examples/char_device/Makefile 2.1 KB
- examples/hello_module/hello_module.c 635 B
- examples/hello_module/Makefile 1.5 KB
- examples/param_module/Makefile 1.6 KB
- examples/param_module/param_module.c 1.3 KB
- examples/proc_module/Makefile 1.9 KB
- examples/proc_module/proc_module.c 1.9 KB
- examples/README.md 5.6 KB
- README.md 4.0 KB
- references/alinux4-repo.md 985 B
- references/kernel-resources.md 795 B
- scripts/build-kernel.sh 11 KB runs code
- scripts/check-env.sh 3.1 KB runs code
- scripts/install-deps.sh 1.9 KB runs code
- scripts/setup.sh 3.5 KB runs code
- scripts/test-module.sh 4.1 KB runs code
- scripts/verify-env.sh 5.9 KB runs code
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.
- 2d ago First seen · 677 lines · 112 tokens per session scan B 2242de3ff52a
kernel-dev is a skill published in the GitHub repository alibaba/anolisa (614 stars, last pushed 3d ago), licensed Apache-2.0. It adds 112 tokens to every session and 4,926 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
beevibe-team-mesh-negotiation
Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…
beevibe-verify-pr
CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…
beevibe-pre-task-setup
Cold-start git workspace setup for a fresh beevibe task. Use at the start of a session whose intent has a block but NO or block — i.e. the first dispatch of this task. Checks for an existing repo clone, pulls the base branch if present (clone if missing), prunes any per-task worktrees from earlier tasks whose work has…
beevibe-use-repo
You are the child agent inside a fresh Docker sandbox. Borrow the given GitHub repo, produce a real artifact for the goal, and export it. Do not review the repo. The proof is that it works.
spec-converge
Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration, decision-completeness, lessons-aware) and real cross-model external reviewers routed through the agent's own installed CLIs (codex → GPT-tier, gemini → Gemini-tier; one pass per available…
beevibe-discover-repo
Find the best GitHub repo for a goal, then call userepo to run it in a sandbox. Use whenever the user's goal requires a capability you don't have natively and you haven't been given a specific repo.