glab-cli

glab-cli is a skill for Claude Code, Codex from flc1125/skills. It costs 95 tokens per session (1,637 once invoked), scanned A, original, MIT.

A reference and workflow for glab, GitLab’s command-line tool. GitLab is a service for hosting code, tracking issues, reviewing changes, and running automated build and test jobs.

In plain words
What is it for?
It is for repository, merge request, issue, CI/CD, release, and GitLab API tasks using glab commands.
Why use it?
It helps developers use the right GitLab project and server context, including GitLab installations managed by a company rather than gitlab.com.

Skill for Claude CodeCodex

Part of the flc-skills plugin — 30 skills shipped together

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/flc1125/skills/glab-cli
Any agent
npx skills add flc1125/skills --skill glab-cli
Clone the repo
git clone --depth 1 https://github.com/flc1125/skills

Made for: Claude Code, Codex.

Or install flc-skills, the plugin that ships this one along with the rest of its 30 skills.

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-cli

README.md
[![agentmods](https://agentmods.dev/badge/skills/flc1125/skills/glab-cli.svg)](https://agentmods.dev/skills/flc1125/skills/glab-cli)
Your own site
<a href="https://agentmods.dev/skills/flc1125/skills/glab-cli"><img src="https://agentmods.dev/badge/skills/flc1125/skills/glab-cli.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,637 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 $0.00095 $0.01637
Opus 5 $0.00048 $0.00818
Sonnet 5 $0.00019 $0.00327
Haiku 4.5 $0.00010 $0.00164

Measured 4d ago against content hash d843e18051d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

glab-cli 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 4d 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.

skills/glab-cli/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GLab CLI

Use glab with host-aware defaults instead of hardcoding gitlab.com.

Workflow

Follow this order unless the user explicitly asks for a single command.

1. Let glab use the current context by default

Do not run host detection by default.

In a Git repository, prefer:

glab <command>

Only add GITLAB_HOST, --hostname, or -R when the task targets another repo or another instance, or when glab resolves the wrong context.

2. Detect the platform only when context is unclear or failing

Check git remote -v only when:

  • glab resolves to the wrong instance
  • auth checks fail against an unexpected host
  • the repository has both GitHub and GitLab remotes
  • multiple GitLab hosts are present
  • the task targets a different instance than the current directory

Rules:

  • Prefer a GitLab remote over any GitHub or Bitbucket remote.
  • If the remote host is gitlab.com, treat the platform as gitlab.com.
  • If the remote host is anything else, treat the platform as self-managed-or-dedicated.
  • If multiple GitLab hosts appear in git remote -v, treat the result as ambiguous and confirm before any write operation.
  • If GITLAB_HOST is already set, let it override the remote-derived host.

If git remote -v does not show a GitLab remote:

  • check whether the user is in the intended repository
  • ask for the GitLab host or repository URL only if the task is otherwise blocked
  • avoid guessing gitlab.com for a private installation

If multiple GitLab hosts are present in git remote -v, do not silently pick one for write operations. Confirm the target or set GITLAB_HOST explicitly first.

3. Reuse explicit context only when needed

For repository-scoped commands, prefer one of these patterns:

glab <command>
GITLAB_HOST="$host" glab <command>
glab <command> -R "$repo"
GITLAB_HOST="$host" glab <command> -R "$repo"

Decision rules:

  • If the current directory is already the target GitLab repository, keep using bare glab commands.
  • If the command targets another repository on the same instance, add -R "$repo".
  • If the command targets another GitLab instance, set GITLAB_HOST="$host" and add -R "$repo" when the command is repository-scoped.
  • For glab api, prefer --hostname "$host" when calling an instance other than the current repository context.

Read the full file on GitHub · 212 lines

Files

What ships with it

2 files beside SKILL.md 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. 4d ago First seen · 212 lines · 95 tokens per session scan A d843e18051d7

Subscribe to this mod's changes

glab-cli is a skill published in the GitHub repository flc1125/skills (36 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,637 once invoked, about $0.0005 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

gemini

Use when the user requests to run Gemini CLI for code analysis, refactoring, or automated editing.

devohmycode/gemini · 22 tokens

iflytek-hyper-tts

Use when user asks to synthesize speech, convert text to audio, or read text aloud. 讯飞超拟人语音合成 - 支持文本转语音、语音合成(发音人/语速/语调/音量/输出格式)。大模型语音合成技能。语音合成, 文字转语音, 超拟人, TTS.

iflytek/iFly-Skills · 92 tokens

iflytek-pdf-image-ocr

AI-powered OCR service for images and PDF documents using iFlytek's advanced recognition APIs.

iflytek/iFly-Skills · 81 tokens

iflytek-translate

Translate text using iFlytek's Machine Translation API (机器翻译). Supports 70+ language pairs.

iflytek/iFly-Skills · 65 tokens

iflytek-contract-intelligence-review

Use when user asks to review contracts, detect contract risks, or perform compliance checks. 合同智能审核 - 对合同扫描件、图片合同、双语合同进行完整审核。 覆盖 OCR 识别、条款分析、风险检测、合规校对、翻译摘要全流程。 适用于法务审核、采购合同审查、供应链合规检查等场景。 关键词:合同审核、风险检测、条款分析、合规校对、contract review、risk detection。.

iflytek/iFly-Skills · 116 tokens

iflytek-image-understanding

Use when user asks to analyze an image, describe image contents, or answer questions about a picture. iFlytek Image Understanding (图片理解) — analyze and answer questions about images using Spark Vision model. WebSocket API, pure Python stdlib, no pip dependencies.

iflytek/iFly-Skills · 61 tokens