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.
npx skills add odyssey4me/agent-skills --skill gitlabgit clone --depth 1 https://github.com/odyssey4me/agent-skillsWrote 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.
[](https://agentmods.dev/skills/odyssey4me/agent-skills/gitlab)<a href="https://agentmods.dev/skills/odyssey4me/agent-skills/gitlab"><img src="https://agentmods.dev/badge/skills/odyssey4me/agent-skills/gitlab/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/odyssey4me/agent-skills/gitlab"><img src="https://agentmods.dev/badge/skills/odyssey4me/agent-skills/gitlab.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 211 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.01953 |
| Opus 5.5 | $0.00021 | $0.00781 |
| Sonnet 5.5 | $0.00010 | $0.00391 |
| Haiku 4.5 | $0.00005 | $0.00195 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab Skill
This skill provides GitLab integration using the official glab CLI tool. A Python wrapper script produces markdown-formatted output for read/view operations. Action commands (create, merge, close, comment) should use glab directly.
Network access
GitLab commands (glab and the Python wrapper) require outbound HTTPS to GitLab API and authentication endpoints, or the configured self-managed GitLab host. Git fetch/push requires HTTPS or SSH to the repository host. Remote operations require outbound network access. If the agent environment restricts it, obtain access through that environment's approval or network controls before the first remote command, reusing authorization already granted. Local help and file processing do not need network access. Skill instructions do not grant network permission. Report DNS, connection, and timeout failures as network errors; do not reset credentials to resolve them. If approved access also fails, stop and report it. Authentication and permission errors require user action.
Resolving script paths
SKILL_DIR in the examples is the directory containing this loaded SKILL.md.
Set it to that absolute path before running commands; do not assume the agent
sets this shell variable. Quote the script path if it contains spaces.
Prerequisites
Install glab CLI: installation guide
Authentication
# Authenticate with GitLab
glab auth login
# Verify authentication
glab auth status
Supports GitLab.com, GitLab Dedicated, and GitLab Self-Managed instances. See GitLab CLI Authentication for details.
Script Usage
The wrapper script (scripts/gitlab.py) formats output as markdown. Use it for read/view operations to get agent-consumable output. Use glab directly for action commands (create, merge, close, comment). See permissions.md for read/write classification of each command.
What ships with it
3 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.
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.
- 1mo ago Changed · +9 lines 3c494a5e92ae
- 2mo ago First seen · 263 lines · 52 tokens per session scan A b447cf499421
gitlab is a skill published in the GitHub repository odyssey4me/agent-skills (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 1,953 once invoked, about $0.0002 per session on Opus 5.5. 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.
gitlab compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gitlabodyssey4me/agent-skills | Skill | 13 | yesterday | Apache-2.0 | A | 52 | Claude Code, Codex |
| deployment-patternsaffaan-m/ECC | Skill | 298k | 5d ago | MIT | A | 41 | Claude Code, Kiro |
| agent-github-modesruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 21 | Claude Code |
| baby-sitlangchain-ai/open-swe | Skill | 11k | yesterday | MIT | A | 30 | Claude Code, Codex |
| chinese-git-workflowjnMetaCode/superpowers-zh | Skill | 8.5k | 11d ago | MIT | A | 69 | Claude Code |
| atmos-hookscloudposse/atmos | Skill | 1.4k | yesterday | Apache-2.0 | A | 46 | Claude Code |
| atmos-procloudposse/atmos | Skill | 1.4k | yesterday | Apache-2.0 | A | 38 | Claude Code |