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/knuckles-team/gitlab-api/gitlab-issuesnpx skills add Knuckles-Team/gitlab-api --skill gitlab-issuesgit clone --depth 1 https://github.com/Knuckles-Team/gitlab-apiWhat 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 | $0.00128 | $0.01040 |
| Opus 5 | $0.00064 | $0.00520 |
| Sonnet 5 | $0.00026 | $0.00208 |
| Haiku 4.5 | $0.00013 | $0.00104 |
Grade A, and why
gitlab-issues 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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitLab Issues
Domain-typed access to GitLab Issues for work-item review and triage — at project scope and across a whole group / organization.
When to use
- Review / triage the issues for a project (by state, label, milestone, assignee).
- Review issues affecting a whole group / organization (spans its subgroups).
- Fetch a single issue by
issue_iid. - Create, update (labels/assignee/state), or delete an issue.
When NOT to use
- Merge requests / reviews →
gitlab-merge-request-review. - Pipeline/job status →
gitlab-pipelines. - Branch/commit/tag/project reads →
gitlab-repositories.
Prerequisites & environment
Connect via the mcp-client skill against the gitlab-api MCP server.
| Variable | Required | Notes |
|---|---|---|
GITLAB_URL |
✅ | GitLab instance base URL |
GITLAB_TOKEN |
✅ | Access token with api scope for writes |
GITLAB_SSL_VERIFY |
optional | TLS verification toggle |
Full env/tag matrix: the mcp-client reference agent-tools/mcp-client/references/gitlab-api.md.
MCP_TOOL_MODE (condensed|verbose|both) selects the condensed vs. one-to-one verbose tools.
Tools & actions
| Condensed tool | Actions |
|---|---|
gitlab_issues |
get, get_group, create, update, delete |
Key parameters
project_id— for project-scopedget(and required forcreate/update/delete); numeric id orgroup/projectpath.group_id— required forget_group(issues across the group and its subgroups).issue_iid— required for singleget/update/delete(project-scoped#iid).data— field→value forcreate/update(title,description,labels,assignee_ids,milestone_id,state_event:close|reopen). Read filters:state,labels,assignee_username,milestone,order_by,sort.
Recipes (params_json)
Review open bug issues for a project, newest first:
{"project_id":"platform/agent-utilities","state":"opened","labels":"bug","order_by":"created_at","sort":"desc","per_page":25}
Review every open issue across a group / organization:
{"group_id":"platform","state":"opened","per_page":50}
Create an issue:
{"project_id":"platform/agent-utilities","data":{"title":"Fleet ontology: gitlab domain missing runners link","labels":"ontology,enhancement"}}
Close an issue:
{"project_id":"platform/agent-utilities","issue_iid":17,"data":{"state_event":"close"}}
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.
- yesterday First seen · 88 lines · 128 tokens per session scan A 8269c7db34bf
gitlab-issues is a skill published in the GitHub repository Knuckles-Team/gitlab-api (10 stars, last pushed 3d ago), licensed MIT. It adds 128 tokens to every session and 1,040 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
rtk-triage
Triage complet RTK : exécute issue-triage + pr-triage en parallèle, puis croise les données pour détecter doubles couvertures, trous sécurité, P0 sans PR, et conflits internes. Sauvegarde dans claudedocs/RTK-YYYY-MM-DD.md. Args: "en"/"fr" pour la langue (défaut: fr), "save" pour forcer la sauvegarde.
fastapi-guard
Production-ready security middleware for FastAPI. Use when adding IP filtering, rate limiting, per-route security decorators, route-resolution strict mode, global behavior rules, passive/log-only mode, or Guard Agent SaaS telemetry to a FastAPI app. Covers SecurityMiddleware setup, SecurityConfig tuning, and the…
Security Audit Reporter
Triage raw security-scan findings (hardcoded secrets, injection patterns, vulnerable dependencies) into a prioritized, actionable security audit report. Use for security audit, code audit, vulnerability triage, and risk review.
k8s-incident-triage
Read-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.
weather
Get current weather and forecasts.