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/jmrplens/gitlab-mcp-server/upstream-contributionnpx skills add jmrplens/gitlab-mcp-server --skill upstream-contributiongit clone --depth 1 https://github.com/jmrplens/gitlab-mcp-serverWrote 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/jmrplens/gitlab-mcp-server/upstream-contribution)<a href="https://agentmods.dev/skills/jmrplens/gitlab-mcp-server/upstream-contribution"><img src="https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/upstream-contribution.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00698 |
| Opus 5 | $0.00020 | $0.00349 |
| Sonnet 5 | $0.00008 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
upstream-contribution 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upstream Contribution — GitLab client-go
Contribute bug fixes, missing endpoint wrappers, or features to the upstream GitLab API client library used by this project.
Before Starting
- Identify the specific gap or bug in
gitlab.com/gitlab-org/api/client-go/v2 - Verify it's not already fixed in the latest release
- Check existing issues/MRs on the upstream project
Upstream Project
- Repository: https://gitlab.com/gitlab-org/api/client-go
- Language: Go
- Branch model:
main(default) - CI: GitLab CI with Go tests
- Style: Standard Go conventions,
gofmt,golangci-lint
Steps
1. Fork and clone
# Fork via GitLab UI, then:
git clone https://gitlab.com/YOUR_USER/client-go.git
cd client-go
git remote add upstream https://gitlab.com/gitlab-org/api/client-go.git
git fetch upstream
2. Create feature branch
git checkout -b fix/endpoint-name upstream/main
3. Implement the fix
Follow existing patterns in the codebase:
- Services in individual files (e.g.,
branches.go,issues.go) - Types match GitLab REST API v4 JSON responses
- Use
*int,*string,*boolfor optional fields in option structs - Follow existing error handling patterns
4. Add tests
- Table-driven tests matching existing style
- Use
httptestfor mock API responses - Test both success and error cases
5. Run CI checks locally
go test ./...
golangci-lint run
6. Commit and push
git commit -m "feat: add EndpointName service method"
git push origin fix/endpoint-name
7. Create merge request
- Target:
mainbranch on upstream - Title:
feat: add EndpointName service method(conventional commit style) - Description: explain the use case, link to GitLab API docs
- Reference this MCP server project as the consumer
8. Update MCP server after merge
Once the upstream MR is merged and released:
go get gitlab.com/gitlab-org/api/client-go/v2@latest
go mod tidy
Rules
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 · 102 lines · 40 tokens per session scan A 34032553166c
upstream-contribution is a skill published in the GitHub repository jmrplens/gitlab-mcp-server (33 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 698 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
kayba-stage-5-action-plan
Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations. Trigger when the user says "run stage 5", "make action plan", "triage skills", or when invoked by the kayba-pipeline orchestrator. Requires eval outputs from stages 1-4.
kayba-stage-2-domain-context
Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. Trigger when the user says "run stage 2", "gather context", "domain context", or when invoked by the kayba-pipeline orchestrator.
playwright-screen-recording
Record browser test videos with Playwright for PR review and bug fix verification.
kayba-stage-1-api-analysis
Fetch pre-computed insights from the Kayba API and build a structured summary. Does NOT upload traces or trigger generation — analysis is assumed to already exist. Trigger when the user says "run stage 1", "get insights", "fetch skills", "kayba analyze", or when invoked by the kayba-pipeline orchestrator. Requires the…