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
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 alibaba/anolisa --skill qwenpaw-usagegit clone --depth 1 https://github.com/alibaba/anolisaWrote 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/qwenpaw-usage)<a href="https://agentmods.dev/skills/alibaba/anolisa/qwenpaw-usage"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/qwenpaw-usage/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/qwenpaw-usage"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/qwenpaw-usage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 Privilege Escalation · line 275 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Privilege Escalation · line 253 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 MCP Rug Pull · line 338 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 314 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00084 | $0.03273 |
| Opus 5.5 | $0.00034 | $0.01309 |
| Sonnet 5.5 | $0.00017 | $0.00655 |
| Haiku 4.5 | $0.00008 | $0.00327 |
Grade B, and why
qwenpaw-usage scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo tar xzf qwenpaw-workspace.tar.gz -C "$MOUNT_PATH" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:8088/api/agent/status | head -20 How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QwenPaw 命令行使用技巧
本 Skill 覆盖两类高频场景：心跳（Heartbeat）任务配置 和 打包部署 QwenPaw 实例到其他服务器。
场景一：添加 / 修改心跳（Heartbeat）任务
什么是心跳
心跳是 QwenPaw 的定时自检机制：按固定间隔读取 HEARTBEAT.md 的内容作为用户消息发给 QwenPaw，QwenPaw 执行后可选择将回复投递到上次对话的频道。适合做「定期自检、每日摘要、定时提醒」。
操作步骤
1. 编写 HEARTBEAT.md
文件位于工作目录下，默认路径：~/.qwenpaw/HEARTBEAT.md。
可通过环境变量 QWENPAW_HEARTBEAT_FILE 更改文件名。
直接用文本编辑器或 cat / echo 写入即可，内容是每次心跳要问 QwenPaw 的问题：
# Heartbeat checklist
- 扫描收件箱紧急邮件
- 查看未来 2h 的日历
- 检查待办是否卡住
- 若安静超过 8h，轻量 check-in
文件为空则跳过心跳，不会触发任何操作。
2. 配置心跳参数
心跳参数有两层配置：
- 全局默认：
~/.qwenpaw/config.json→agents.defaults.heartbeat（对所有智能体生效） - 智能体独立：
~/.qwenpaw/workspaces/{agent_id}/agent.json→heartbeat（覆盖全局默认）
可用字段：
| 字段 | 类型 | 默认值 | 说明 |
|---|---|---|---|
every |
string | "30m" |
间隔，支持 Nh、Nm、Ns 组合（如 "1h30m"） |
target |
string | "main" |
"main" 仅执行不投递；"last" 发到上次对话的频道/用户 |
activeHours |
object/null | null |
可选活跃时段限制 |
activeHours.start |
string | "08:00" |
开始时间（HH:MM） |
activeHours.end |
string | "22:00" |
结束时间（HH:MM） |
配置示例（每 30 分钟自检，不发到频道，写在 config.json 中）：
"agents": {
"defaults": {
"heartbeat": {
"every": "30m",
"target": "main"
}
}
}
配置示例（每 1 小时，发到上次频道，限 08:00-22:00，写在 agent.json 中）：
"heartbeat": {
"every": "1h",
"target": "last",
"activeHours": { "start": "08:00", "end": "22:00" }
}
3. 生效方式
保存文件后，若服务正在运行会自动加载新配置。也可通过以下命令手动重载：
qwenpaw daemon reload-config
注意：频道和 MCP 配置的变更需要在对话中执行
/daemon restart或重启进程后才能生效。
心跳 vs 定时任务
| 心跳 | 定时任务 (cron) | |
|---|---|---|
| 数量 | 每个智能体只有一份 HEARTBEAT.md | 可创建多个 |
| 间隔 | 一个全局间隔 | 每个任务独立 cron 表达式 |
| 投递 | 仅 main（不发）或 last（上次频道） |
每个任务独立指定频道和用户 |
| 适用 | 固定的一套自检/摘要 | 多条不同时间、不同内容的任务 |
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 · 352 lines · 84 tokens per session scan B a4499e65366a
qwenpaw-usage is a skill published in the GitHub repository alibaba/anolisa (603 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 3,273 once invoked, about $0.0003 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
agent-swarm
Install, self-host, deploy, operate, or use agent-swarm. Covers Docker Compose, Kubernetes, configuration, coding agents, the admin UI, integrations, and connections.
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, files and bash over the agent-fs drive (ctx.fs…
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…