gitlab

A connection to GitLab for examining source-code projects, commits, deployments, pipelines, and merge requests. GitLab is a service for storing code and reviewing changes made by a team.

In plain words
What is it for?
Use it to list projects, check CI/CD pipelines, inspect commits and file differences, review merged changes, suggest code fixes, create merge requests, and commit Terraform files.
Why use it?
It helps trace incidents back to recent code changes or failed deployments and can prepare fixes for review.

Skill for Claude CodeCodex

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 skills/arvo-ai/aurora/gitlab
Any agent
npx skills add Arvo-AI/aurora --skill gitlab
Clone the repo
git clone --depth 1 https://github.com/Arvo-AI/aurora

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 803 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 $0.00025 $0.00803
Opus 5 $0.00013 $0.00402
Sonnet 5 $0.00005 $0.00161
Haiku 4.5 $0.00003 $0.00080

Measured 2d ago against content hash 98e637910ea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade 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 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.

server/chat/backend/agent/skills/integrations/gitlab/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitLab Integration

Overview

GitLab integration for investigating code changes during Root Cause Analysis and managing code fixes. Connected via org-level Group Access Token. Instance: {base_url}

Instructions

Single Tool — Multiple Actions

All GitLab operations use the gitlab tool with an action parameter:

Action Purpose Required Params
list_projects Discover connected projects
deployment_check CI/CD pipelines repo (or auto)
commits Recent commits + correlation repo (or auto)
diff File changes for a commit commit_sha
merge_requests Merged MRs in time window repo (or auto)
suggest_fix Propose a code fix file_path, suggested_content, fix_description, root_cause_summary
apply_fix Create MR from suggestion suggestion_id
commit_terraform Push Terraform files repo, commit_message

RCA Investigation Workflow

Code changes are the most common root cause of incidents. Investigate GitLab BEFORE deep-diving into infrastructure.

Step 1 — Discover projects: gitlab(action='list_projects') — returns all connected projects.

Step 2 — Check pipelines (did something just ship?): gitlab(action='deployment_check', repo='namespace/project', incident_time='<ISO8601>') Finds failed pipelines and pipelines completed within 2 hours of the incident.

Step 3 — Check commits (what code changed?): gitlab(action='commits', repo='namespace/project', incident_time='<ISO8601>') Lists commits with automatic suspicious-commit flagging.

Step 4 — Inspect suspicious changes: gitlab(action='diff', repo='namespace/project', commit_sha='<sha>') Shows file-level additions/deletions. Prioritize config/infra files.

Step 5 — Check merged MRs: gitlab(action='merge_requests', repo='namespace/project', incident_time='<ISO8601>') Finds MRs merged in the time window; recently merged MRs are flagged.

Post-RCA Remediation (after user approval)

Read the full file on GitHub · 83 lines

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 · 83 lines · 25 tokens per session scan A 98e637910ea9

Subscribe to this mod's changes

gitlab is a skill published in the GitHub repository Arvo-AI/aurora (401 stars, last pushed 4d ago), licensed Apache-2.0. It adds 25 tokens to every session and 803 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 2026-08-30.

Related

Other skills, from other repositories