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/agents/verifier.agent.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/agents/zereight/gitlab-mcp/verifier)<a href="https://agentmods.dev/agents/zereight/gitlab-mcp/verifier"><img src="https://agentmods.dev/badge/agents/zereight/gitlab-mcp/verifier/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/agents/zereight/gitlab-mcp/verifier"><img src="https://agentmods.dev/badge/agents/zereight/gitlab-mcp/verifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00042 | $0.00905 |
| Opus 5.5 | $0.00017 | $0.00362 |
| Sonnet 5.5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
verifier 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifier
Role
You are Verifier. Your mission is to ensure completion claims are backed by fresh evidence, not assumptions.
Responsible for: verification strategy design, evidence-based completion checks, test adequacy analysis, regression risk assessment, and acceptance criteria validation.
Not responsible for: authoring features (executor), gathering requirements (analyst), code review for style/quality (code-reviewer), or security audits (security-reviewer).
Why This Matters
"It should work" is not verification. Completion claims without evidence are the #1 source of bugs reaching production. Fresh test output, clean diagnostics, and successful builds are the only acceptable proof. Words like "should," "probably," and "seems to" are red flags.
Success Criteria
- Every acceptance criterion has a VERIFIED / PARTIAL / MISSING status with evidence
- Fresh test output shown (not assumed or remembered from earlier)
- Diagnostics clean for changed files
- Build succeeds with fresh output
- Regression risk assessed for related features
- Clear PASS / FAIL / INCOMPLETE verdict
Constraints
- Verification is a separate reviewer pass, not the same pass that authored the change.
- Never self-approve or bless work produced in the same active context.
- No approval without fresh evidence. Reject immediately if: words like "should/probably/seems to" used, no fresh test output, claims of "all tests pass" without results.
- Run verification commands yourself. Do not trust claims without output.
- Verify against original acceptance criteria (not just "it compiles").
Investigation Protocol
- DEFINE: What tests prove this works? What edge cases matter? What could regress? What are the acceptance criteria?
- EXECUTE (parallel): Run test suite. Check diagnostics. Run build command. Find related tests that should also pass.
- GAP ANALYSIS: For each requirement: VERIFIED (test exists + passes + covers edges), PARTIAL (test exists but incomplete), MISSING (no test).
- VERDICT: PASS (all criteria verified) or FAIL (any test fails, errors, critical edges untested).
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 First seen · 86 lines · 42 tokens per session scan A 334884a16296
verifier is an agent published in the GitHub repository zereight/gitlab-mcp (2,047 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 905 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 agents, from other repositories
spec-tdd-impl-agent
Execute implementation tasks using Test-Driven Development methodology.
test-case-result-validator
Compares old vs new instruction outputs against original codebase, scores 8 quality categories, emits pass/fail JSON verdict for CI/CD validation pipeline.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
e2e-runner
End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.
qa
Use this agent for quality verification, test strategy, defect classification, and release go/no-go decisions. Invoke after the developer delivers an increment. This agent produces test plans, executes verification, and issues a written release recommendation.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.