ANOLISA is a server-side operating layer for AI agent workloads that provides terminal access, token-saving tool-output compression, runtime controls, security, observability, skills, memory, and sandbox management. It is for running and supervising agents from a Linux terminal while retaining an existing shell, agent framework, and sandbox. The catalogue add-ons are components of its agent operating environment and workflows.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/alibaba/anolisanpx agentmods add skills/alibaba/anolisa/kernel-devWrote 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/alibaba/anolisa/kernel-dev)<a href="https://agentmods.dev/skills/alibaba/anolisa/kernel-dev"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/kernel-dev/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/alibaba/anolisa/kernel-dev"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/kernel-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 32 findings, up to high
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 →
- high Tool Misuse · line 359 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium Privilege Escalation · line 50 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 59 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 67 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 119 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 122 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 129 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 226 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 343 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 346 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 377 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 386 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 405 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 420 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 443 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 536 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 551 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 70 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 135 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 174 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00112 | $0.04926 |
| Opus 5.5 | $0.00045 | $0.01970 |
| Sonnet 5.5 | $0.00022 | $0.00985 |
| Haiku 4.5 | $0.00011 | $0.00493 |
Grade B, and why
kernel-dev scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo yum install -y \ Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
git ccache dwarves wget curl kmod \ How it starts
The opening of the file, as written. The whole thing — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kernel Development - Linux 内核研发自动化
核心定位
五大功能：
- 依赖检测与安装 - 自动检测并安装内核开发所需的软件包
- 工具链安装 - 安装编译器（gcc）、make、git 等开发工具
- 内核 devel 包安装 - 下载并安装当前系统内核的 devel 包
- 内核编译 - 支持两种编译方法：
- SRPM 方法：Alinux4 官方内核，输出 RPM 包，适合生产环境
- Upstream 方法：kernel.org 最新内核，编译快速，适合新特性测试
- Module 编译测试 - 测试编译示例内核 module
支持架构：
x86_64— Intel/AMD 64 位服务器aarch64— ARM 64 位服务器（如倚天 710）
重要约束：
- 🔒 需要 root 权限执行内核相关操作
- 📦 仅Linux操作系统
- ⚠️ 内核编译会消耗大量系统资源（建议至少 4GB 内存）
- ⏱️ 编译时间：SRPM 方法 1-3 小时，Upstream 方法 30-60 分钟
快速开始
一键搭建开发环境
# 1. 检测系统架构
ARCH=$(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.
- 1mo ago First seen · 677 lines · 112 tokens per session scan B 2242de3ff52a
kernel-dev is a skill published in the GitHub repository alibaba/anolisa (603 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 112 tokens to every session and 4,926 once invoked, about $0.0004 per session on Opus 5.5. 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
apps
Build and iterate on schema-backed Swarm Apps with live models, named queries, custom actions, and json-render interfaces using the app-upsert, app-get, app-list, and app-patch tools.
kapso-whatsapp
How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and…
swarm-scripts
Bulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline script-run, named script-upsert, durable launch-script-run). Covers the script-vs-tool rubric, the authoring contract (args first, ctx second), the seed catalog, connections and secrets, dbquery, and exposing a script as an API.
composio
Use Composio from Agent Swarm through the agent-swarm x composio CLI route, the swarmx MCP tool, or a registered ctx.api.composio script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router…
motion-design-video-analysis
Reverse-engineer a short motion-design / product-update video (animation technique, timing and easing, composition, transitions, likely tooling, vibe, audio) and produce a rebuild spec someone can build from. Default path is one call to google/gemini-3.8-flash over sampled frames, then a mandatory by-eye check of…
open-prompt-showreel
Make a design-led motion-graphics video (showreel, eval comparison, feature or bug-hunt story) from one open prompt. Claude Opus at max effort designs, codes and renders the whole thing itself in a scratch dir, with no template and no repo PR. Use for any "make a video for X" / "do a showreel for Y" / "a little…