zzop

A self-hosted plugin marketplace with a tool that traces links across separate code repositories, such as which frontend calls which backend route and database table.

In plain words
What is it for?
Use it to inspect frontend-to-backend-to-database contracts across repositories and find calls that do not connect as expected.
Why use it?
It helps AI agents check these connections using exact matches instead of guessing, while showing where the analysis cannot see enough.

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 eezz4/zzop
agentmods
npx agentmods add plugins/eezz4/zzop/marketplace
Clone the repo
git clone --depth 1 https://github.com/eezz4/zzop

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

zzop 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.

The scan reads marketplace.json. This mod also ships 1 executable file (hooks/bootstrap.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude-plugin/marketplace.json · 16 lines

What it actually says

{
  "name": "zzop",
  "description": "Self-hosted marketplace for the zzop plugin — deterministic cross-repo contract analysis (frontend calls x backend routes x DB tables) for AI agents.",
  "owner": {
    "name": "eezz4",
    "url": "https://github.com/eezz4"
  },
  "plugins": [
    {
      "name": "zzop",
      "source": "./",
      "description": "Deterministic cross-repo contract analysis for AI agents: which frontend calls hit which backend endpoints (and which don't) — exact joins, disclosed blind spots, no guessing. Run /plugin install after adding this marketplace; the plugin then fetches its own self-contained binary (5 platforms, no Node) on first session — nothing to put on PATH. That first session does NOT list the zzop tools yet (its tool list was settled before the download finished): restart Claude Code once and they appear. On Windows the download step needs a POSIX shell; Git for Windows supplies one, and a plugin marketplace is a git clone anyway."
    }
  ]
}
Files

What ships with it

3 files beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 16 lines scan A 769b55b81da3

Subscribe to this mod's changes

zzop is a plugin published in the GitHub repository eezz4/zzop (2 stars, last pushed 17d ago), licensed MIT. 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.