Borrowing it
Nothing to install: this file belongs to jmrplens/gitlab-mcp-server. 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/jmrplens/gitlab-mcp-server/main/.github/skills/go-safe-move-refactor/SKILL.mdgit 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/go-safe-move-refactor)<a href="https://agentmods.dev/skills/jmrplens/gitlab-mcp-server/go-safe-move-refactor"><img src="https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/go-safe-move-refactor/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/jmrplens/gitlab-mcp-server/go-safe-move-refactor"><img src="https://agentmods.dev/badge/skills/jmrplens/gitlab-mcp-server/go-safe-move-refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.03353 |
| Opus 5.5 | $0.00020 | $0.01341 |
| Sonnet 5.5 | $0.00010 | $0.00671 |
| Haiku 4.5 | $0.00005 | $0.00335 |
Grade A, and why
go-safe-move-refactor 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 16d 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Safe Move Refactor
Primary Directive
Move one or more Go source files from one package to another while maintaining compilation at every intermediate step. This skill implements the "bridge pattern" — keep old code working via forwarding stubs while new code is established, then remove bridges after verification.
When to Use
- Moving a
.gofile from one package to another - Extracting a set of functions/types into a new package
- Consolidating multiple files into a single sub-package
- Splitting a large package into smaller ones
Core Principle: Never Break Compilation
Every change must be an atomic step that leaves go build ./... passing. The sequence is:
1. Create destination → 2. Copy & transform → 3. Add forwarding stubs → 4. Verify → 5. Update consumers → 6. Remove stubs → 7. Verify
Process
Step 1: Pre-Flight Check
go build ./... # Must pass
golangci-lint run --build-tags e2e ./... # Must pass
go test ./... # Record baseline (should pass)
Record:
- Source file path:
${srcFile}(e.g.,internal/tools/branches.go) - Source package:
${srcPkg}(e.g.,tools) - Destination directory:
${dstDir}(e.g.,internal/tools/branches/) - Destination package:
${dstPkg}(e.g.,branches)
Discovery check (before any move): The client-go API defines the canonical domain structure. Verify you have the complete picture:
- Inspect client-go types: Run
go doc gitlab.com/gitlab-org/api/client-go/v3.{Type}for the domain's key types to understand the canonical fields and API contract - List all non-test handler files in the source package to find everything that exists
- Check
action_specs.goand catalog aggregation for the domain's canonical runtime exposure - Look for related files (e.g., a domain might span
{domain}.go+{domain}_extra.go) - If the domain's catalog group has a generated tool reference page (
site/src/content/docs/reference/tools/<group>.mdx, written bymake gen-tool-reference;<group>is the group's tool name withoutgitlab_and with hyphens, sogitlab_merge_requestismerge-request.mdx), read it for supplementary user-facing context, but do NOT skip the move if there is none. A move never edits that page: it changes only if the move changes what the catalog serves (a tool name, an action ID, a description, a tier or a schema), and thenmake gen-tool-referencerewrites it
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.
- 16d ago Changed f05fcfcc3fb3
- 1mo ago Changed 400abb0adb50
- 1mo ago Changed · -2 lines 5ccb17c7ca3f
- 1mo ago First seen · 365 lines · 50 tokens per session scan A 26c1d5973b10
go-safe-move-refactor is a skill published in the GitHub repository jmrplens/gitlab-mcp-server (46 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 3,353 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 skills, from other repositories
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).
golang-benchmark
Run reproducible Go benchmarks, profiling, benchstat and CI regression analysis.
golang-observability
Instrument Go services using slog, OpenTelemetry, Prometheus and profiling.
go-expert
Expert-level Go development with Go 1.22+ features, concurrency, standard library, and production-grade best practices. Use when the user mentions concurrency, microservices, or backend, or when the task involves idiomatic Go, goroutines and channels, context-based cancellation, or writing an HTTP server.
go-code-review
Use when reviewing Go code or checking code against community style standards. Also use proactively before submitting a Go PR or when reviewing any Go code changes, even if the user doesn't explicitly request a style review. Does not cover language-specific syntax — delegates to specialized skills.
go-concurrency
Use when writing concurrent Go code — goroutines, channels, mutexes, or thread-safety guarantees. Also use when parallelizing work, fixing data races, or protecting shared state, even if the user doesn't explicitly mention concurrency primitives. Does not cover context.Context patterns (see go-context).