openlinker

A command set for finding, inspecting, configuring, and calling OpenLinker Agents. OpenLinker is a system for discovering and running reusable agents through local tools.

In plain words
What is it for?
Use it to find a suitable OpenLinker Agent, run or inspect an existing task, serve Claude Code as an OpenLinker Agent, or repair the OpenLinker CLI when requested.
Why use it?
It gives the coding agent a defined route for handling agent discovery, existing run IDs, progress, results, artifacts, and setup requests.

Command

Part of the openlinker plugin — 6 skills, 4 commands, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add commands/openlinker-ai/openlinker-plugin/openlinker
Clone the repo
git clone --depth 1 https://github.com/OpenLinker-ai/openlinker-plugin

Or install openlinker, the plugin that ships this one along with the rest of its 6 skills, 4 commands, 1 MCP server.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00181
Opus 5 $0.00006 $0.00090
Sonnet 5 $0.00002 $0.00036
Haiku 4.5 $0.00001 $0.00018

Measured 2d ago against content hash 70519618adfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

platforms/claude/openlinker/commands/openlinker.md · 20 lines

What it actually says

Route the user's request to the bundled OpenLinker skills:

  • Use find-and-run-agent for discovery, task recommendations, Agent details, authorized execution, progress, results, and artifacts.
  • Use inspect-openlinker-run when the request starts from an existing Run ID, including diagnosis or explicit cancellation.
  • Use serve-openlinker-agent when the user wants Claude Code to become a callable OpenLinker Agent or asks about Agent Mode/session reuse.
  • Use setup-openlinker-cli only when the user asks to install/repair the CLI or a required CLI capability is missing.

Use the bundled local MCP tools. Do not use Hosted MCP or direct Core HTTP as a fallback.

User request: $ARGUMENTS

Changes

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.

  1. 2d ago First seen · 20 lines · 12 tokens per session scan A 70519618adfd

Subscribe to this mod's changes

openlinker is a command published in the GitHub repository OpenLinker-ai/openlinker-plugin (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 12 tokens to every session and 181 once invoked, about $0.0001 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.