linear-remote

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.

Security

Grade A, and why

linear-remote 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.

linear-remote/.claude-plugin/plugin.json · 28 lines

What it actually says

{
  "name": "linear-remote",
  "description": "Read-first wrapper around the Linear GraphQL API. One-call issue context (comments + relations + state), name-resolved teams/projects/states/labels, --from-markdown turns design docs into issues, --wait on webhook-driven state transitions. Zero API-key leakage.",
  "version": "0.4.0",
  "author": {
    "name": "Oliver Southgate",
    "url": "https://github.com/osouthgate"
  },
  "homepage": "https://github.com/osouthgate/agent-plus-skills",
  "repository": "https://github.com/osouthgate/agent-plus-skills",
  "license": "MIT",
  "keywords": [
    "linear",
    "issues",
    "project-management",
    "graphql",
    "agent-tools",
    "triage"
  ],
  "agent_plus_version": ">=0.7",
  "refresh_handler": {
    "command": "linear-remote whoami --json",
    "timeout_seconds": 10,
    "identity_keys": ["name", "email"],
    "failure_mode": "soft"
  }
}

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.

Related

Other plugins, from other repositories