preflight-check

A setup checker for connections to outside services such as GitHub, Atlassian tools, and UniFi network management. It checks access before work begins.

In plain words
What is it for?
Use it before working with GitHub repositories, pull requests, or issues; Jira or Confluence; or UniFi networks. It can also check integrations when you explicitly ask it to.
Why use it?
It helps reveal missing login details or broken connections early, before a task fails halfway through.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add trtmn/agent-plugins
agentmods
npx agentmods add plugins/trtmn/agent-plugins/preflight-check
Clone the repo
git clone --depth 1 https://github.com/trtmn/agent-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

preflight-check 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.

plugins/preflight-check/.claude-plugin/plugin.json · 6 lines

What it actually says

{
  "name": "preflight-check",
  "version": "1.0.0",
  "description": "Validate all external service connections before starting work. Trigger this skill proactively whenever a task involves GitHub (gh CLI, repos, PRs, issues), Atlassian (Jira, Confluence, any mcp__claude_ai_Atlassian__ tool), or UniFi (network management, UNIFI_API_KEY). Also trigger when the user explicitly says \"preflight\", \"check connections\", \"validate services\", \"are my APIs working\", \"check my integrations\", \"test my setup\", or \"verify access\". If any external service call fails unexpectedly during a task, trigger this skill to diagnose the issue. The goal is to catch auth problems early rather than failing mid-task."
}
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. yesterday First seen · 6 lines scan A 5200aea148d3

Subscribe to this mod's changes

preflight-check is a plugin published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 4d ago), licensed Unlicense. 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.