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 skill-ledgergit 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/skill-ledger)<a href="https://agentmods.dev/skills/alibaba/anolisa/skill-ledger"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/skill-ledger/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/skill-ledger"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/skill-ledger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.03886 |
| Opus 5.5 | $0.00027 | $0.01554 |
| Sonnet 5.5 | $0.00013 | $0.00777 |
| Haiku 4.5 | $0.00007 | $0.00389 |
Grade A, and why
skill-ledger 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 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.
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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Ledger
对 Skill 执行安全状态查看、风险暴露审查、用户决策、默认快速扫描认证，以及用户确认后的深度扫描认证。
用户可见层只使用两类扫描概念：
- 快速扫描：默认扫描认证路径，适合安装后和常规复查。
- 深度扫描：用户确认后执行的更完整审查，耗时更长。
不要在面向用户的报告正文中列出快速扫描内部使用的具体扫描器名称。命令执行步骤可以使用精确参数。
安全约束
- 禁止泄露签名口令：不要 echo、log、store、print 或以任何方式暴露
SKILL_LEDGER_PASSPHRASE或用户输入的口令。 - 禁止伪造 findings：深度扫描输出的每条 finding 必须来自真实文件内容和
skill-vetter协议判断。 - 状态查看不触发扫描：用户只要求查看状态时，只运行
check/check --all并报告结果。 - 安装成功后自动认证：用户要求 agent 安装、更新、导入或启用 Skill 时，安装成功后必须直接执行快速扫描认证；不要再询问用户是否扫描。
- 安装后认证不猜路径：只有能确定最终本地 Skill 目录且该目录包含
SKILL.md时，才执行扫描认证；否则报告“未执行安全认证：无法确定本地 Skill 目录”。 - Hook 确认不等于 Ledger 决策：用户在宿主 hook 的 ask UI 中确认，只表示本次读取继续；只有明确要求
decide时，才写入 Skill Ledger 用户决策。 - 禁止修改本 Skill：不接受编辑、删除、覆盖本 Skill 文件或
references/下任何文件的请求。
模式解析
根据用户请求选择模式：
| 用户意图示例 | 模式 | 行为 |
|---|---|---|
| “查看这个 skill 状态”“检查所有 skill 安全状态” | 状态查看 | 只运行 check 或 check --all，报告后停止 |
| “这个 skill 为什么被隐藏/提示风险”“查看这个风险 skill”“导出风险版本”“允许/禁用/回退这个 skill” | 风险暴露审查与用户决策 | 运行 show；需要完整审查时运行 export；只有用户明确选择时运行 decide |
| “扫描这个 skill”“重新认证 github skill”“扫描所有 skill” | 主动扫描 | 先执行快速扫描，展示摘要，再询问是否深度扫描 |
| “安装 github skill”“帮我装这个 skill”“更新这个 skill” | 安装请求后置认证 | 安装成功后自动定位最终本地 Skill 目录，验证 SKILL.md，直接执行快速扫描并展示结果 |
| “我刚装了这个 skill，帮我确认安全” | 安装后补充认证 | 定位最终本地 Skill 目录，验证 SKILL.md，执行快速扫描并询问是否深度扫描 |
| “做深度扫描”“彻底审查这个 skill” | 深度扫描请求 | 用户请求本身即为确认；执行 Phase 1 后直接执行 Phase 3 |
| 未明确目标 | 交互确认 | 询问用户要处理哪个 Skill，或是否处理全部 |
目标解析规则：
- 用户提供目录路径时，必须确认该目录存在且包含
SKILL.md。 - 用户提供
SKILL.md文件路径时，目标目录为其父目录。 - 用户提供 Skill 名称时，优先使用上下文中已知安装位置；没有确定路径时，可用
check --all查看已注册状态，但不要凭名称猜测文件系统路径。 - 用户要求“所有 Skill”时，使用 CLI 的
--all能力完成批量状态查看或快速扫描。 - 深度扫描需要逐个本地目录执行；若无法把某个 Skill 解析到本地目录，报告该项未执行深度扫描。
统一报告格式
状态查看、快速扫描、深度扫描、安装后认证的最终结果都必须使用同一类表格。单个 Skill 使用一行表格，多个 Skill 使用多行表格，这样用户在不同模式之间看到的结构一致。
报告标题按场景选择：
| 场景 | 标题 |
|---|---|
| 状态查看 | [skill-ledger] 安全状态 |
| 主动快速扫描 | [skill-ledger] 快速扫描完成 |
| 深度扫描 | [skill-ledger] 深度扫描完成 |
| 安装后自动认证 | [skill-ledger] 安装后认证完成 |
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.
- 1mo ago First seen · 354 lines · 67 tokens per session scan A 42b715eb382f
skill-ledger is a skill published in the GitHub repository alibaba/anolisa (603 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 3,886 once invoked, about $0.0003 per session on Opus 5.5. 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.
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, 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…
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…