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 shell-scriptinggit 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/shell-scripting)<a href="https://agentmods.dev/skills/alibaba/anolisa/shell-scripting"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/shell-scripting/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/shell-scripting"><img src="https://agentmods.dev/badge/skills/alibaba/anolisa/shell-scripting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
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 →
- medium Output Handling · line 193 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
- medium Prompt Injection · line 365 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 365 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 367 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 369 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 372 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium MCP Rug Pull · line 397 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00060 | $0.03631 |
| Opus 5.5 | $0.00024 | $0.01452 |
| Sonnet 5.5 | $0.00012 | $0.00726 |
| Haiku 4.5 | $0.00006 | $0.00363 |
Grade C, and why
shell-scripting scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$TMP_DIR" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
require_cmd curl How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When this skill is activated, always start your first response with the 🧢 emoji.
Shell Scripting
Shell scripting is the art of automating tasks through the Unix shell - combining built-in commands, control flow, and process management to build reliable CLI tools and automation workflows. This skill covers production-quality bash and zsh scripting: robust error handling, portable argument parsing, safe file operations, and the idioms that separate fragile one-liners from scripts that hold up in production.
When to use this skill
Trigger this skill when the user:
- Asks to write or review a bash or zsh script
- Needs to parse command-line arguments or flags
- Wants to automate a CLI workflow or task runner
- Asks about exit codes, signal trapping, or error handling in shell
- Needs to process files, lines, or streams from the terminal
- Asks about here documents, process substitution, or subshells
- Wants a portable script that works across bash, zsh, and sh
Do NOT trigger this skill for:
- Python or Node.js CLI tools (shell is the wrong tool for complex logic)
- Scripts that require structured data parsing at scale (use a real language instead)
Key principles
- Always use
set -euo pipefail- Start every non-trivial script with this.-eexits on error,-utreats unset variables as errors,-o pipefailcatches failures in pipelines. Without this, silent failures hide bugs for weeks. - Quote everything - Always double-quote variable expansions:
"$var","$@","${array[@]}". Unquoted variables break on whitespace and glob characters. The only exceptions are intentional word splitting and arithmetic contexts. - Check dependencies upfront - Verify required commands exist before the script runs. Fail fast at the top with a clear error, not halfway through a destructive operation.
- Use functions for reuse and readability - Extract logic into named functions.
Shell functions support local variables (
local), can return exit codes, and make scripts testable. Amain()function at the bottom with a guard is idiomatic. - Prefer shell built-ins over external commands -
[[ ]]over[ ],${var##*/}overbasename,${#str}overwc -c. Built-ins are faster, more portable, and avoid spawning subshells. Useprintfoverechofor reliable output formatting.
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 · 398 lines · 60 tokens per session scan C 824c89974b23
shell-scripting is a skill published in the GitHub repository alibaba/anolisa (603 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 3,631 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, 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
shell-scripting
A guide to writing Bash shell scripts, which automate command-line tasks on Linux and similar systems. It covers variables, arrays, conditions, loops, functions, and safer script structure.
bash-scripting
Use when writing or hardening a shell script that must survive another machine — a CI step, install script, cron job, git hook, devcontainer entrypoint: strict-mode leaks, quoting/word-splitting, arrays, trap cleanup, bash-vs-POSIX portability, ShellCheck findings. NOT CI workflow structure, runners, caching or matrix…
mainframe
Discover MAINFRAME read-only shell helpers and route durable agent authority through its control plane when available.
mainframe
Pi shell policy, explicit task checkpoints, and runtime status. Use for Mainframe status, shell-policy questions, or resuming checkpointed project work.
mainframe
Discover MAINFRAME read-only shell helpers and route durable agent authority through its control plane when available.
bash-scripting-safe
Write safe, robust Bash scripts — set -euo pipefail, quoting, word splitting, error handling, idempotency, and common data-loss gotchas.