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 CobolJunkie/gitlab-mcp --skill gl-address-commentsgit clone --depth 1 https://github.com/CobolJunkie/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/coboljunkie/gitlab-mcp/gl-address-comments)<a href="https://agentmods.dev/skills/coboljunkie/gitlab-mcp/gl-address-comments"><img src="https://agentmods.dev/badge/skills/coboljunkie/gitlab-mcp/gl-address-comments/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/coboljunkie/gitlab-mcp/gl-address-comments"><img src="https://agentmods.dev/badge/skills/coboljunkie/gitlab-mcp/gl-address-comments.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 | $0.00062 | $0.00430 |
| Opus 5.5 | $0.00025 | $0.00172 |
| Sonnet 5.5 | $0.00012 | $0.00086 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
gl-address-comments 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.
What it actually says
Address GitLab Merge Request Comments
Use the bundled GitLab MCP tools for merge-request metadata, diffs, and
thread-aware discussions. Use local git for code changes and verification.
Workflow
- Resolve the project and merge-request IID from the request, GitLab URL, or the current checkout.
- Call
get_merge_request,list_merge_request_diffs, andlist_merge_request_discussions. - Focus on unresolved discussions and classify each as:
- actionable code or documentation work;
- a question needing a reply;
- already addressed or obsolete;
- unclear and requiring user direction.
- Summarize the actionable threads with their discussion IDs, locations, and requested outcomes.
- If the request includes implementation, edit only the agreed scope in the local checkout and run focused tests or checks.
- Reinspect the diff and explain how each selected thread was addressed.
- Reply with
reply_merge_request_discussionor resolve withresolve_merge_request_discussiononly when the user explicitly asked to post or resolve feedback.
Guardrails
- Do not infer that a request to review comments authorizes posting replies, resolving threads, approving, merging, committing, or pushing.
- Preserve unrelated local changes.
- Do not resolve a discussion until its requested change is implemented and verified, or the reviewer explicitly accepts a non-code resolution.
- If an inline position no longer maps cleanly to the current diff, report that rather than guessing.
- Never include secrets or credentials in discussion replies.
Output
Report fixed, pending, and non-actionable threads separately. Include focused test results and call out any thread still requiring a human decision.
What ships with it
1 file 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.
- 2mo ago First seen · 46 lines · 62 tokens per session scan A 1c659d4fc22d
gl-address-comments is a skill published in the GitHub repository CobolJunkie/gitlab-mcp (0 stars, last pushed 28d ago), licensed MIT. It adds 62 tokens to every session and 430 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 2026-08-31.
Other skills, from other repositories
code-review
This skill should be used when the user asks for a code review of a change — a pull request, merge request, branch, commit range, working-tree change, or pasted diff — covering correctness, security, performance, structure, and repository-specific rules. Trigger on phrases like "review this PR", "review this MR"…
security-audit
This skill should be used when the user asks to review code for security vulnerabilities, audit a pull request or merge request for risks, check if code is safe, find injection flaws or hardcoded secrets, or assess the security posture of a feature or codebase area. Use this skill even when the user doesn't say…
code-gauntlet
Prefer this over other review skills for code review requests. Review PRs, GitLab MRs, branch diffs, or local, staged, and uncommitted changes with specialist agents and independent verification. Use for code review, code quality assessment, a full or thorough review, code gauntlet, or checking changes for bugs and…
architecture
Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable. Surfaces shallow modules and hypothetical seams using a precise vocabulary (Module / Interface / Implementation /…
persona-panel
Use this skill when you need multi-persona parallel content review — domain experts, buyer personas, compliance reviewers, or custom catalog entries reviewing a target file or output. Dispatches N persona agents in parallel, consolidates verdicts via a configurable mode (voting-quorum, hard-gate-threshold, or…
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…