Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add OpenLinker-ai/openlinker-plugin/plugin install openlinkerWrote 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/openlinker-ai/openlinker-plugin/setup-plugin-host)<a href="https://agentmods.dev/skills/openlinker-ai/openlinker-plugin/setup-plugin-host"><img src="https://agentmods.dev/badge/skills/openlinker-ai/openlinker-plugin/setup-plugin-host/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/openlinker-ai/openlinker-plugin/setup-plugin-host"><img src="https://agentmods.dev/badge/skills/openlinker-ai/openlinker-plugin/setup-plugin-host.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00052 | $0.00378 |
| Opus 5.5 | $0.00021 | $0.00151 |
| Sonnet 5.5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
setup-plugin-host 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl and tar; it does not need Go, administrator rights or the platform CLI. What it actually says
Set Up the Plugin Host
Resolve the installed Plugin root from PLUGIN_ROOT, CLAUDE_PLUGIN_ROOT, or this Skill's location (two directories above this directory). Standalone Skills do not include a host installer; in that case install the native marketplace Plugin first.
Run node "<plugin-root>/scripts/install-plugin-host.mjs" --plan and show the
pinned version, GitHub release URL, current platform, SHA-256 and destination.
Invoking this Skill or /openlinker:install-plugin-host is explicit installation
intent; then run the same command without --plan. It installs only the locked
host for the current platform into private Plugin data. It needs Node.js 20+,
curl and tar; it does not need Go, administrator rights or the platform CLI.
Run node "<plugin-root>/scripts/resolve-plugin-host.mjs" --require plugin.serve
to verify. Reload plugins or start a new task after successful installation so
the native MCP server restarts. Report the installed version and path only.
Do not enable Agent Mode, register an Agent or print credentials during setup.
Do not substitute latest, change the lock, disable TLS/checksums, install a CLI as a host, or download anything during ordinary tool calls. If installation fails, report its exact error; checksum failures leave existing versions intact. If an existing locked installation was damaged, identify that exact immutable installation directory and get explicit repair intent before removing it and rerunning setup. Never remove Agent configuration, session or state directories.
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 · 30 lines · 52 tokens per session scan A 9aed13ae3023
setup-plugin-host is a skill published in the GitHub repository OpenLinker-ai/openlinker-plugin (0 stars, last pushed 13d ago), licensed Apache-2.0. It adds 52 tokens to every session and 378 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
plugin-publish
A release guide for publishing Zhin.js plugins to npm, the JavaScript package registry, and to the Zhin plugin marketplace. It covers package metadata, versioning, release checks, and submission requirements.
plugin-develop
A development guide for adding features to Zhin.js plugins, such as chat commands, AI tools, middleware, scheduled tasks, and console pages. Zhin.js is the plugin system it targets.
commands-create-slash-command
Create or edit reusable Agent Zero /commands with YAML and text/Python templates.
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.
dbt-strategy
Use when creating or modifying dimensional dbt models in warehouse-backed analytics projects. Covers a four-layer warehouse architecture (sources/staging/core/marts), naming conventions, no-alias SQL rule, surrogate-key and missing-record patterns, incremental strategies, deduplication, and common project macros. Use…
data-quality
Use when adding or reviewing data quality tests for dbt models in warehouse-backed analytics projects. Covers dbt generic tests, singular tests (assert.sql), accepted-values macros, dbtutils patterns, cross-system consistency tests, and warehouse-oriented validation. Use when writing data tests, creating assert.sql…