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 CobolJunkie/gitlab-mcpnpx agentmods add plugins/coboljunkie/gitlab-mcp/claudegit clone --depth 1 https://github.com/CobolJunkie/gitlab-mcpGrade A, and why
gitlab 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "gitlab",
"version": "0.1.1",
"description": "Inspect GitLab projects, triage merge requests and issues, debug CI/CD, address review feedback, and publish changes.",
"license": "MIT",
"mcpServers": "./.mcp.json"
}
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 · 9 lines scan A 5a71bd75d682
gitlab is a plugin published in the GitHub repository CobolJunkie/gitlab-mcp (0 stars, last pushed 13d 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.
Other plugins, from other repositories
code-gauntlet
Plugin marketplace listing 1 plugin: code-gauntlet.
code-gauntlet
Adversarial multi-agent code review. Your PR runs a gauntlet of up to seven concern-specialized agents, then survives deterministic verification, skeptical validation, and a blind challenge before anything reaches you. Prompt injection defense and flexible delivery (PR/MR comments, markdown, chat). Supports GitHub and.
air
Plugin marketplace listing 1 plugin: air.
air
Automated PR code review for GitHub — 6 specialized agents + Codex, wiki-based pattern learning, self-review/respond/re-review modes, model tiering, session-scoped /tmp, pre-commit drift-check hook, and Managed Agent CI option.
gitlab-mcp
GitLab MCP server with GraphQL discovery and team activity tools.
asana-sweep
Scheduled AI sweep of your Asana tasks: triage, dedupe, and open GitLab issues that trigger an AI coding harness.