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 agentmods add skills/jie123108/shellink/shellink-clinpx skills add jie123108/Shellink --skill shellink-cligit clone --depth 1 https://github.com/jie123108/ShellinkWhat 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 | $0.00049 | $0.00764 |
| Opus 5 | $0.00024 | $0.00382 |
| Sonnet 5 | $0.00010 | $0.00153 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
shellink-cli scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/jie123108/Shellink/main/install.sh -o /tmp/shellink-install.sh How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shellink CLI
This skill depends on the local shellink command. Do not implement or connect
to the Unix socket protocol directly.
Prerequisite: install shellink if missing
Before any Shellink operation, ensure shellink is available:
command -v shellink
If it is missing:
-
macOS / Linux — install the prebuilt binary (latest release):
curl -fsSL https://raw.githubusercontent.com/jie123108/Shellink/main/install.sh -o /tmp/shellink-install.sh cat /tmp/shellink-install.sh sh /tmp/shellink-install.shPin a version if needed:
curl -fsSL https://raw.githubusercontent.com/jie123108/Shellink/main/install.sh -o /tmp/shellink-install.sh cat /tmp/shellink-install.sh sh /tmp/shellink-install.sh --version v0.1.0The installer places
shellinkin$HOME/.local/bin. If that directory is not onPATH, add it for the current session (and tell the user to persist it in their shell profile):export PATH="$HOME/.local/bin:$PATH" -
Windows — prebuilt binaries are not published. Tell the user to build from source (Node.js 22.19+, npm):
git clone https://github.com/jie123108/Shellink.git cd Shellink npm install npm run build # CLI: ./node_modules/.bin/shellink
After install, verify:
shellink -V
shellink server status --json
To upgrade an existing standalone binary:
shellink upgrade --check --json
shellink upgrade --yes --json
npx skills update shellink-cli only updates this skill, not the shellink binary.
Operate sessions
Always read the installed command reference before operating sessions or profiles, and follow it. Re-read it rather than relying on memorized commands:
shellink agent-doc
Add --json for stable machine-readable output. A command starts the user
daemon automatically.
Long-running operations
Host agents (e.g. Cursor) wait only ~30s for a shell command before
backgrounding it. Keep every CLI call short: for anything that may exceed
~25s, use --detach and poll the returned job.
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.
- yesterday First seen · 104 lines · 49 tokens per session scan A b0e51cf26a4c
shellink-cli is a skill published in the GitHub repository jie123108/Shellink (5 stars, last pushed 10d ago), licensed MIT. It adds 49 tokens to every session and 764 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cli-anything-jumpserver
Stateful CLI harness for JumpServer bastion host management. Supports asset, user, permission, account, session, audit, and operations management via REST API, with both one-shot and interactive REPL modes.
oly
Use when starting a long-running or interactive CLI command with oly, especially when it may need later input, should be detachable, or should keep durable logs for supervision and resume.
oly-apps
Use when building a web app/api to present rich output or interactive experiences to users.
tui-explorer
Discover and replay terminal UI paths using agent-tui. Use when you need to launch a TUI app, explore navigation with bounded BFS, generate markdown acceptance tests, and verify those tests repeatedly. Do not use for web or desktop GUI automation.
si-coder
Zero human involvement full-stack deployment to Dokploy. Automatically create GitHub repositories, push local code via SSH, setup projects, configure Next.js and self-hosted Convex DB (via Docker Compose), and trigger deployments via REST API.
winkterm-remote
远程操作 WinkTerm —— 默认用 MCP 或 winkterm CLI（WebSocket 长连接，长任务不被反代超时切断），HTTP 仅在 CLI 不可用时兜底。管理 SSH 连接（增删改查）、新建本地/SSH 终端、发命令并读输出、获取终端快照、SSH 文件传输。当需要远程执行 shell 命令、运维服务器、或在受控终端里跑命令时使用。.