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 backend-skillgit 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/backend-skill)<a href="https://agentmods.dev/skills/alibaba/anolisa/backend-skill"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/backend-skill/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/backend-skill"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/backend-skill.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 | $0.00046 | $0.03954 |
| Opus 5.5 | $0.00018 | $0.01582 |
| Sonnet 5.5 | $0.00009 | $0.00791 |
| Haiku 4.5 | $0.00005 | $0.00395 |
Grade A, and why
add-backend 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 — 542 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a Backend to Security Middleware
This skill walks through the complete, end-to-end process of adding a backend (Rust or Python) to the security middleware, wiring it into the router, and exposing it through the CLI.
Unified interface: Both Rust and Python backends implement the same
execute(ctx, **kwargs) → ActionResultcontract. The middleware doesn't care about the implementation language.
Backend Type Selection
| Type | Use Case | Pros | Cons |
|---|---|---|---|
| rust | Performance-critical, CPU-intensive tasks | High performance, memory safety | Requires Rust toolchain, compilation |
| python | Rapid development, glue code, existing libraries | Fast iteration, rich ecosystem | Slower execution, GIL limitations |
Naming Convention
Derive all identifiers from the backend_name argument:
| Concept | Rule | Example (backend_name = "code verify") |
|---|---|---|
| action_name | lowercase, underscores | code_verify |
| Backend class | PascalCase + Backend |
CodeVerifyBackend |
| Python module | {action_name}.py |
code_verify.py |
| lifecycle category | same as action_name | code_verify |
Rust-specific (only when backend_type=rust):
| Concept | Rule | Example |
|---|---|---|
| Rust function | same as action_name | code_verify |
| Request struct | PascalCase + Request |
CodeVerifyRequest |
| Response struct | PascalCase + Response |
CodeVerifyResponse |
1. Architecture Overview
Both backend types follow the same execution flow:
agent-sec-cli ──→ security_middleware.invoke("{action_name}", **kwargs)
│
├─ router.get_backend("{action_name}")
│ └─ _REGISTRY["{action_name}"] → "security_middleware.backends.{action_name}"
│ └─ lazy import → {ActionName}Backend()
│
├─ backend.execute(ctx, **kwargs) → ActionResult
│ │
│ ├─ [Rust] from agent_sec_cli._native import {action_name}
│ │ {action_name}(json_in) → json_out
│ │
│ └─ [Python] import {module_path}
│ module.function(**kwargs) → result
│
└─ lifecycle.post_action() → SecurityEvent → JSONL
What ships with it
4 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.
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 · 542 lines · 46 tokens per session scan A 4c147c3cb426
add-backend is a skill published in the GitHub repository alibaba/anolisa (603 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 3,954 once invoked, about $0.0002 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
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…
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.
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…