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 structured-world/gitlab-mcp --skill gitlab-work-itemsgit clone --depth 1 https://github.com/structured-world/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/structured-world/gitlab-mcp/gitlab-work-items)<a href="https://agentmods.dev/skills/structured-world/gitlab-mcp/gitlab-work-items"><img src="https://agentmods.dev/badge/skills/structured-world/gitlab-mcp/gitlab-work-items/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/structured-world/gitlab-mcp/gitlab-work-items"><img src="https://agentmods.dev/badge/skills/structured-world/gitlab-mcp/gitlab-work-items.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 | $0.00052 | $0.00432 |
| Opus 5.5 | $0.00021 | $0.00173 |
| Sonnet 5.5 | $0.00010 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
gitlab-work-items 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 4d 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
Work with GitLab work items
Use the selected connection and verified namespace. The server handles GraphQL work-item type discovery; do not hardcode GitLab type IDs or call a separate REST issues endpoint. Inspect the advertised schema because type availability depends on the instance.
- Find existing items before creating one:
browse_work_items,{"action":"list","namespace":"example-group/backend","types":["ISSUE"],"state":["OPEN"],"first":20}. Use returned pagination cursors for relevant additional pages. - Read details with
{"action":"get","id":"returned-work-item-id"}. Reuse returned IDs for updates and follow-ups, including IDs of labels, milestones and assignees; do not invent them. - Use a project namespace for issues/tasks and a group namespace for epics. Existing scope and permissions apply at both levels. Report unavailable types/actions instead of substituting a different item type.
- When the user asks to publish a concrete task, create it with
manage_work_item, for example{"action":"create","namespace":"example-group/backend","workItemType":"ISSUE","title":"Add connection diagnostics","description":"Problem, implementation and acceptance criteria"}. Write a single actionable plan with the requested scope, useful validation and dependencies. Exclude secrets, private planning identifiers and unsupported estimates. - For a requested update, inspect the current item and apply the specific fields using
updateand the returned ID. Verify the persisted result withgetand report its link. Delete/close/link only when requested.
An empty successful listing is distinct from an authorization error. A submitted mutation with a timeout has an unknown outcome: reconcile using the returned ID or a narrow listing before retrying. Do not bypass read-only policy, switch accounts or request credentials to complete an unauthorized write.
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.
- 4d ago First seen · 17 lines · 52 tokens per session scan A 4eef32606085
gitlab-work-items is a skill published in the GitHub repository structured-world/gitlab-mcp (8 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 432 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 2026-10-10.
Other skills, from other repositories
report-issue
File a bug or feature request against this repository (cyanheads/git-mcp-server) using the gh CLI. Use for tool logic bugs, git provider misbehavior, transport issues, auth/config problems, or new feature proposals.
add-export
Add a new subpath export to the @cyanheads/mcp-ts-core package. Use when creating a new public API surface that consumers import from a dedicated subpath (e.g., @cyanheads/mcp-ts-core/newutil).
Verification Planner
Mandates generation of testassertions.json during planning. v7.2.0 enhanced with severity gates (warn/gate/abort), dependency chains, and Claw-as-Validator support.
find-contact
A contact and company lookup for amoCRM, a customer-management system. It searches existing records, checks for duplicates, and can create a new contact or company with notes and related activity.
pipeline-report
A procedure for reporting the state of an amoCRM sales funnel, a set of stages that deals move through before they are won or lost. It groups deals by stage and value and checks how long they have been inactive.
complete-task
A workflow for completing or reassigning ELMA365 business-process tasks. ELMA365 is a business process management system in which tasks move a process from one step to the next.