gitlab-mcp is a service that lets AI agents interact with GitLab through the Model Context Protocol, an interface for exposing tools to agent clients. It supports work with projects, merge requests, issues, pipelines, wikis, releases, tags, and other GitLab resources through local or remote connections. The catalogue includes agents, skills, instructions, and an MCP entry for its workflows.
Borrowing it
Nothing to install: this file belongs to zereight/gitlab-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zereight/gitlab-mcp/main/.github/skills/ccg/SKILL.mdgit clone --depth 1 https://github.com/zereight/gitlab-mcpWrote 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/zereight/gitlab-mcp/ccg)<a href="https://agentmods.dev/skills/zereight/gitlab-mcp/ccg"><img src="https://agentmods.dev/badge/skills/zereight/gitlab-mcp/ccg/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/zereight/gitlab-mcp/ccg"><img src="https://agentmods.dev/badge/skills/zereight/gitlab-mcp/ccg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.00615 |
| Opus 5.5 | $0.00019 | $0.00246 |
| Sonnet 5.5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
ccg 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 2mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCG - Claude-Codex-Gemini Tri-Model Orchestration
Route a task through three AI models in parallel, then synthesize their outputs into one unified answer.
When to Use
- Backend/analysis + frontend/UI work in one request
- Code review from multiple perspectives
- Cross-validation where models may disagree
- Fast parallel input without full team orchestration
When NOT to Use
- Simple, straightforward tasks → execute directly
- Already clear on approach → use
/omg-autopilot - Need coordinated multi-agent work → use
/team
Requirements
- Codex CLI:
npm install -g @openai/codex - Gemini CLI:
npm install -g @google/gemini-cli - If either CLI is unavailable, continue with whichever provider works
Execution Protocol
1. Decompose Request
Split the user request into:
- Codex prompt: architecture, correctness, backend, risks, test strategy
- Gemini prompt: UX/content clarity, alternatives, edge-case usability, docs polish
- Synthesis plan: how to reconcile conflicts
2. Invoke Advisors
Run both advisors via CLI in parallel:
# Run in terminal
codex "<codex prompt>"
gemini "<gemini prompt>"
Or via VS Code's selectChatModels() API if available:
Promise.all([
model_openai.sendRequest(codex_prompt),
model_google.sendRequest(gemini_prompt)
])
3. Collect Results
Gather outputs from both advisors.
4. Synthesize
Return one unified answer with:
- Agreed recommendations
- Conflicting recommendations (explicitly called out)
- Chosen final direction + rationale
- Action checklist
Fallbacks
| Scenario | Action |
|---|---|
| One provider unavailable | Continue with available + Claude synthesis |
| Both unavailable | Fall back to Claude-only answer |
Example
/ccg Review this PR - architecture/security via Codex and UX/readability via Gemini
Output:
=== CCG Synthesis ===
## Agreed
- Authentication middleware needs rate limiting
- Error messages should be more user-friendly
## Conflicting
- Codex: Use middleware pattern for validation
- Gemini: Use inline validation for simplicity
→ Chosen: Middleware pattern (consistency with existing codebase)
## Action Checklist
- [ ] Add rate limiting middleware
- [ ] Improve error messages in auth flow
- [ ] Extract validation to middleware layer
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.
- 2mo ago First seen · 101 lines · 48 tokens per session scan A 6439319f98d5
ccg is a skill published in the GitHub repository zereight/gitlab-mcp (2,074 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 615 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.
Other skills, from other repositories
gitlab-merge-request-review
Review and merge GitLab merge requests via the gitlab-api MCP server — by default the MRs assigned to you or where you are a reviewer, optionally scoped to a project, group, or the whole instance. Read an MR, gate it on a green pipeline (pipeline → jobs → job log), then approve, accept/merge, or set…
gitlab-api-development
Develop, test, gate, and release the GitLab REST and GraphQL connector. Use this skill when changing API mappings, governed MCP tools, authentication, tenant selection, KG ingestion, packaged content, or repository gates.
gitlab-pipelines
CI/CD pipeline review on GitLab via the gitlab-api MCP server — review pipeline results for a project, a group, or the whole instance, drill into the CI jobs of a pipeline, and read a job's log; also trigger a pipeline on a ref. Use when the agent must review CI results across a project/group/organization, check…
gitlab-vulnerabilities
Dependency and security-vulnerability review on GitLab via the gitlab-api MCP server — the GitLab counterpart to GitHub Dependabot. Read a project's Dependency List, review a project's or group's security vulnerabilities/findings, and fetch a single vulnerability by ID. Use when the agent must audit a project's…
gitlab-issues
Issue review and tracking on GitLab via the gitlab-api MCP server — review a project's issues, review issues across a whole group/organization, and read, create, update, or close an issue with the domain-typed tool. Use when the agent must triage a project's issues, see every issue affecting a group, open a new issue…
gitlab-merge-request-create
Open a new GitLab merge request against a project via the gitlab-api MCP server — from a source branch into a target branch, with title, description, assignees, reviewers, labels, and remove-source-branch/squash options. Use when the agent must create/open an MR for a project. Do NOT use to review, approve, or merge…