glab

glab is a skill for Claude Code, Codex from aretw0/agents-lab. It costs 30 tokens per session (573 once invoked), scanned A, original, MIT.

A guide for using glab, the command-line tool for GitLab, a service for hosting Git repositories and coordinating software work. It covers issues, merge requests, automated pipelines, and API queries.

In plain words
What is it for?
Use it to list, view, create, close, merge, and check GitLab issues, merge requests, CI pipelines, and their logs.
Why use it?
It makes GitLab actions explicit and repeatable, including the repository to use and the details needed to avoid interactive prompts.

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/aretw0/agents-lab/glab
Any agent
npx skills add aretw0/agents-lab --skill glab
Clone the repo
git clone --depth 1 https://github.com/aretw0/agents-lab

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for glab

README.md
[![agentmods](https://agentmods.dev/badge/skills/aretw0/agents-lab/glab.svg)](https://agentmods.dev/skills/aretw0/agents-lab/glab)
Your own site
<a href="https://agentmods.dev/skills/aretw0/agents-lab/glab"><img src="https://agentmods.dev/badge/skills/aretw0/agents-lab/glab.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 573 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 $0.00030 $0.00573
Opus 5 $0.00015 $0.00287
Sonnet 5 $0.00006 $0.00115
Haiku 4.5 $0.00003 $0.00057

Measured 3d ago against content hash d57867b220db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

glab 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 3d 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.

packages/git-skills/skills/glab/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitLab Skill

Use the glab CLI to interact with GitLab. Always specify --repo namespace/project when not inside a git directory.

Provide all required fields explicitly to avoid interactive prompts:

glab mr create --title "..." --description "..." --yes

Issues

# List open issues
glab issue list --repo namespace/project

# View an issue
glab issue view 42 --repo namespace/project

# Create an issue
glab issue create --title "..." --description "..." --repo namespace/project

# Close an issue
glab issue close 42 --repo namespace/project

Merge Requests

# List MRs
glab mr list --repo namespace/project

# View an MR
glab mr view 55 --repo namespace/project

# Create an MR (always provide title and description)
glab mr create --title "..." --description "..." --yes --repo namespace/project

# Merge an MR
glab mr merge 55 --yes --repo namespace/project

# Check MR CI status
glab mr checks 55 --repo namespace/project

CI / Pipelines

# List recent pipelines
glab ci list --repo namespace/project

# View pipeline status
glab ci status --repo namespace/project

# View detailed pipeline jobs
glab ci view --repo namespace/project

# View logs for a specific job
glab ci trace --repo namespace/project

JSON Output

Use --output json for structured output and pipe to jq:

glab issue list --output json | jq '.[] | "\(.iid): \(.title)"'

glab mr list --output json | jq '.[] | "\(.iid) [\(.source_branch)]: \(.title)"'

# Get MR URL
glab mr view 55 --output json | jq .web_url

API for Advanced Queries

Use glab api for anything not covered by subcommands:

# Get project details
glab api projects/namespace%2Fproject

# List merge requests with specific fields
glab api projects/namespace%2Fproject/merge_requests --field state=opened \
  | jq '.[] | "\(.iid): \(.title)"'

# Paginated results
glab api --paginate projects/namespace%2Fproject/issues | jq '.[].title'

Note: GitLab API uses URL-encoded namespace/project — replace / with %2F.

Read the full file on GitHub · 96 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. 3d ago First seen · 96 lines · 30 tokens per session scan A d57867b220db

Subscribe to this mod's changes

glab is a skill published in the GitHub repository aretw0/agents-lab (11 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 573 once invoked, about $0.0002 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.