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/openlinker-ai/openlinker-plugin/setup-openlinker-clinpx skills add OpenLinker-ai/openlinker-plugin --skill setup-openlinker-cligit clone --depth 1 https://github.com/OpenLinker-ai/openlinker-pluginWhat 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 | $0.00061 | $0.00451 |
| Opus 5 | $0.00030 | $0.00226 |
| Sonnet 5 | $0.00012 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
setup-openlinker-cli 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 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.
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.
What it actually says
Set Up the OpenLinker CLI
Use the Plugin's deterministic resolver and installer. Do not implement an
alternate downloader, install a floating latest, or modify a project file.
Verify First
Resolve the package root from PLUGIN_ROOT, then CLAUDE_PLUGIN_ROOT, or the
installed Skill location. Run scripts/resolve-openlinker-cli from that root.
It checks, in order, OPENLINKER_CLI_BIN, PATH, and the Plugin data directory,
then validates context JSON, surface version, and requested capabilities.
If a compatible CLI is found, report its path, version, and capabilities and
stop. Never print OPENLINKER_USER_TOKEN or other environment values.
Install Only with Explicit Intent
Running this Skill or /openlinker-setup is explicit installation intent.
Before invoking the installer, show:
- the pinned CLI version from
cli-lock.json; - the GitHub release origin;
- the platform/architecture;
- the Plugin data destination.
Then run scripts/install-openlinker-cli from that root on POSIX systems or
scripts/install-openlinker-cli.ps1 on Windows. The installer must select an exact
entry from cli-lock.json, download the archive and adjacent checksum, verify
SHA-256, reject symlink destinations, extract only the expected executable, and
install atomically into Plugin data. A failed check must leave the previous CLI
untouched.
Honor standard HTTP/HTTPS proxy configuration. Do not disable TLS validation, follow a private-network redirect, use credentials from prompts, or fall back to an unverified binary.
After installation, run the resolver again and report only non-sensitive version and capability information. If installation cannot complete, provide the exact failure and the manual fixed-release installation option; do not silently switch the Plugin to remote MCP.
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 · 46 lines · 61 tokens per session scan A 68ef8771c31b
setup-openlinker-cli is a skill published in the GitHub repository OpenLinker-ai/openlinker-plugin (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 61 tokens to every session and 451 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
plugin-init
初始化 Zhin.js 插件项目。Use when asked to create a new plugin, scaffold plugin structure, or set up a plugin project. 引导生成符合 Plugin Runtime 规范的目录结构、package.json、plugin.ts、约定能力目录和 README。.
plugin-publish
发布 Zhin.js 插件到 npm 和 Zhin 插件市场。Use when asked to publish a plugin, prepare for release, check publish readiness, or submit to the Zhin plugin marketplace. 引导完成发布前检查、版本管理和提交流程。.
plugin-develop
Implement Zhin.js plugin features with Plugin Runtime: defineCommand, defineAgentTool, middleware, pages. Use when asked to add a command, register a tool, wire cron, extend middleware, or build a console page. Triggers: 插件开发, add command, 加命令, 写插件功能, defineCommand.
commands-create-slash-command
Create or update Agent Zero slash commands for the built-in Commands plugin. Use when the user asks to add, edit, duplicate, or refine a reusable /command backed by YAML config plus text/python content files.
deepseek-harness
Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.
research-extraction
Deep extraction of research corpora into structured knowledge documents using a Workflow-driven subagent/reviewer pattern. Use when you have raw source documents (theses, papers, reports) and need structured extraction across multiple axes (architecture, messages, algorithms, forms, etc.) with confidence-annotated…