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.
/plugin marketplace add OpenLinker-ai/openlinker-pluginnpx agentmods add plugins/openlinker-ai/openlinker-plugin/marketplacegit clone --depth 1 https://github.com/OpenLinker-ai/openlinker-pluginGrade 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 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
{
"name": "openlinker",
"owner": {
"name": "OpenLinker",
"email": "[email protected]"
},
"description": "Official OpenLinker plugins for Claude Code.",
"plugins": [
{
"name": "openlinker",
"source": "./platforms/claude/openlinker",
"description": "Discover and call OpenLinker Agents, or expose Claude Code as an OpenLinker Runtime Agent.",
"version": "0.1.2",
"author": {
"name": "OpenLinker"
}
}
]
}
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 · 20 lines scan A 90ca20307ae6
openlinker is a plugin published in the GitHub repository OpenLinker-ai/openlinker-plugin (0 stars, last pushed 2d 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
agent-powerups
Reusable AI agent skills, commands, hooks, and workflows for Claude Code, Codex, and Gemini — an Oh My Zsh-style collection of developer powerups.
agent-skills
Skills for knowledge-base research, PDF extraction, and slop-free writing.
agent-skills
Plugin marketplace listing 1 plugin: agent-skills.
agentic-systems
Multi-model orchestration and advisor routing: tri-model review and canonical advisor routing.
codebase-intelligence
Search-first codebase understanding, context retrieval, mapping, pattern detection, and living project intelligence.
codebase-maintenance
Safe refactoring, dead-code removal, legacy modernization, and dependency hygiene.