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.
git clone --depth 1 https://github.com/OpenLinker-ai/openlinker-pluginWrote 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/plugins/openlinker-ai/openlinker-plugin/openlinker)<a href="https://agentmods.dev/plugins/openlinker-ai/openlinker-plugin/openlinker"><img src="https://agentmods.dev/badge/plugins/openlinker-ai/openlinker-plugin/openlinker/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/plugins/openlinker-ai/openlinker-plugin/openlinker"><img src="https://agentmods.dev/badge/plugins/openlinker-ai/openlinker-plugin/openlinker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
openlinker 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 12d 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "openlinker",
"displayName": "OpenLinker",
"version": "0.2.3",
"description": "Call OpenLinker Agents, expose Claude Code as a reusable Agent, and run an isolated Browser Agent.",
"author": {
"name": "OpenLinker",
"email": "[email protected]",
"url": "https://openlinker.ai/"
},
"homepage": "https://openlinker.ai/",
"repository": "https://github.com/OpenLinker-ai/openlinker-plugin",
"license": "Apache-2.0",
"keywords": [
"openlinker",
"agents",
"agent-marketplace",
"a2a",
"cli",
"runtime",
"session-reuse",
"isolated-browser"
],
"skills": "./skills/",
"commands": "./commands/"
}
What it installs
The manifest is a name and a version. 7 skills, 5 commands, 1 MCP server travel with it, and installing the plugin installs all of them — 443 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill find-and-run-agent A 58 tokens
- Skill inspect-openlinker-run A 54 tokens
- Skill use-isolated-browser A 57 tokens
- Skill serve-openlinker-agent A 58 tokens
- Skill setup-openlinker-cli A 59 tokens
- Skill setup-plugin-host A 52 tokens
- Skill openlinker A 43 tokens
- Command openlinker A 12 tokens
- Command install-plugin-host A 13 tokens
- Command openlinker-agent A 16 tokens
- Command use-isolated-browser A 9 tokens
- Command openlinker-setup A 12 tokens
- MCP server openlinker A not measured
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.
- 12d ago Changed da3cc7fa5768
- 13d ago Changed 8ef1cdcc4624
- 1mo ago Changed a9702856dd54
- 1mo ago First seen · 28 lines scan A bf53f510cee9
openlinker is a plugin published in the GitHub repository OpenLinker-ai/openlinker-plugin (0 stars, last pushed 13d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
browser-gateway
Cloud browsers through the hosted BrowserGateway MCP server. When WebFetch is blocked or gets an empty page, Claude retries with a real browser.
codebase-intelligence
Search-first codebase understanding, context retrieval, mapping, pattern detection, and living project intelligence.
connected-apps
Review-first runbooks for connected-app workflows and multi-system deployment sequencing.
data-engineering
Analytics engineering, dbt patterns, BigQuery optimization, data quality, and pipeline workflows.
documentation-systems
Documentation architecture, API reference authoring, ADR writing, readme hardening, and doc quality.
machine-learning-ops
ML pipeline design, experiment tracking, model evaluation, training debugging, and reproducibility.