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 agentmods add skills/frontier-ai-next/mgarlbot/gitlab_apinpx skills add frontier-ai-next/mgarlbot --skill gitlab_apigit clone --depth 1 https://github.com/frontier-ai-next/mgarlbotWhat 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 | $0.00022 | $0.00771 |
| Opus 5 | $0.00011 | $0.00385 |
| Sonnet 5 | $0.00004 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
gitlab_api 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab REST API (gitlab_api tool)
Токен и URL GitLab уже в настройках бота (GITLAB_API_TOKEN, GITLAB_API_URL). Не передавай токен в аргументах и не выводи его в ответ.
Когда использовать
- «покажи MR / issues / pipeline в проекте X»
- «создай issue / merge request»
- «прочитай
.gitlab-ci.ymlиз репо» - «найди проекты / поиск по GitLab»
Для редактирования .gitlab-ci.yml локально — скилл gitlab_pages_ci + shell.
Для чтения/создания через API — только gitlab_api.
project_id
Числовой ID или path: group/subgroup/project (как в URL GitLab).
Типовые вызовы
Список проектов (где я member):
{"action": "list_projects", "params": {"membership": true, "simple": true, "per_page": 20}}
Проект по path:
{"action": "get_project", "project_id": "frontierai/teams/mag/dmas/gmas"}
Merge requests (открытые):
{"action": "list_merge_requests", "project_id": "group/project", "params": {"state": "opened", "per_page": 10}}
Создать MR:
{
"action": "create_merge_request",
"project_id": "group/project",
"params": {
"source_branch": "feature/foo",
"target_branch": "main",
"title": "feat: foo",
"description": "…"
}
}
Issues / pipeline / файл:
{"action": "list_issues", "project_id": "group/project", "params": {"state": "opened"}}
{"action": "list_pipelines", "project_id": "group/project", "params": {"ref": "main", "per_page": 5}}
{"action": "get_file", "project_id": "group/project", "params": {"file_path": "README.md", "ref": "main"}}
{"action": "list_tree", "project_id": "group/project", "params": {"path": "", "ref": "main", "per_page": 50}}
Поиск:
{"action": "search", "params": {"scope": "projects", "search": "mgarlbot"}}
Расширенный запрос (если нужного action нет):
{
"action": "api_request",
"params": {
"method": "GET",
"path": "/projects/123/members",
"query": {"per_page": 20}
}
}
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.
- 3d ago First seen · 89 lines · 22 tokens per session scan A 1e96718a2745
gitlab_api is a skill published in the GitHub repository frontier-ai-next/mgarlbot (17 stars, last pushed 26d ago), licensed MIT. It adds 22 tokens to every session and 771 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.
Other skills, from other repositories
exec-local-docker
Execute a TensorRT-LLM workload locally in Docker. Runs a fully-resolved Docker command in background, monitors completion, reads logs, and reports results. Workflow-agnostic — does not need to know if the workload is pytest, eval, benchmark, or a custom script.
dockerfile-slimming
Reduce container image size and build time with multi-stage builds and ordered layer caching.
Docker Compose Generator
Generates production-ready docker-compose.yml files for any application stack.
agent-comm-hub
本地多智能体通信 Hub（MCP stdio / HTTP-SSE），提供消息、任务编排、共享记忆、进化引擎，暴露 58 个 MCP 工具 + Web 管理面板.
devops-infra
DevOps & Infrastructure (Docker, AWS, Messaging): Helps with Docker configuration, AWS architecture, CI/CD pipelines, Kubernetes, monitoring, and messaging infrastructure (Kafka, SQS, SNS). Use whenever the user wants to review or create Dockerfiles, docker-compose configs, AWS architecture, CI/CD pipelines…
omniwire
Infrastructure layer for AI agent swarms — 88 MCP tools for mesh control, A2A protocol, OmniMesh VPN, CyberSync, web scraping, firewall management, browser automation, and more. 80ms execution.