samber/cc-skills-golang is a collection of reusable agent instructions for Go development, covering areas such as the language, testing, security, and observability. It is for coding agents assisting with production-oriented Golang projects. The catalogue entries are its Go-specific skills, rule, plugin, and instruction.
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 samber/cc-skills-golang --skill golang-how-togit clone --depth 1 https://github.com/samber/cc-skills-golangWrote 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/samber/cc-skills-golang/golang-how-to)<a href="https://agentmods.dev/skills/samber/cc-skills-golang/golang-how-to"><img src="https://agentmods.dev/badge/skills/samber/cc-skills-golang/golang-how-to/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/samber/cc-skills-golang/golang-how-to"><img src="https://agentmods.dev/badge/skills/samber/cc-skills-golang/golang-how-to.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00185 | $0.04210 |
| Opus 5 | $0.00093 | $0.02105 |
| Sonnet 5 | $0.00037 | $0.00842 |
| Haiku 4.5 | $0.00018 | $0.00421 |
Grade A, and why
golang-how-to 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 8d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona: You are a Go skills orchestrator. For every Go task, identify all relevant skills and load them together — a task rarely belongs to a single skill.
Modes:
- Orchestrate — for any Go coding, review, debug, or setup task, load the primary skill plus all applicable secondary skills simultaneously.
- Disambiguate — when two skills seem to overlap, show the boundary table. See disambiguation.md.
- Configure — write the always-load directive for
golang-how-toitself, plus an optional## Required Go skillsblock, to the project's agent-config file (CLAUDE.md, AGENTS.md, or equivalent). Follow project-config.md.
Questions: In Configure mode, ask the user through the environment's question tool — never as plain-text prose. One question at a time, wait for the answer. If the environment has no question tool, ask in prose with the same options.
Dependencies: gopls — go install golang.org/x/tools/gopls@latest; Claude Code's built-in LSP tool also needs ENABLE_LSP_TOOL=1 and a Go language server wired (see Code navigation with gopls).
Skill loading
For each task, load the primary skill and all applicable secondary skills at the same time. Do not wait — load them together at the start.
| Intent | Primary | Also load |
|---|---|---|
| Design an API, choose a pattern | golang-design-patterns |
golang-structs-interfaces, golang-naming |
| Name a type, function, or package | golang-naming |
golang-code-style |
| Handle errors idiomatically | golang-error-handling |
golang-safety (nil-heavy code) |
| Write goroutines, channels, sync | golang-concurrency |
golang-context (if cancellation) |
| Pass deadlines / cancel operations | golang-context |
golang-concurrency (if goroutines) |
| Design structs, embed, use interfaces | golang-structs-interfaces |
golang-design-patterns |
| Database queries and transactions | golang-database |
golang-error-handling, golang-security |
| Build a gRPC service | golang-grpc |
golang-testing, golang-error-handling |
| Build a GraphQL API | golang-graphql |
golang-testing, golang-error-handling |
| Build a CLI command tree | golang-spf13-cobra |
golang-cli, golang-spf13-viper (if config) |
| Layer config from flags/env/file | golang-spf13-viper |
golang-spf13-cobra |
| Write tests | golang-testing |
golang-stretchr-testify (if using testify) |
| Apply optimization patterns | golang-performance |
golang-benchmark (measure first) |
| Measure with pprof / benchstat | golang-benchmark |
golang-performance (fix), golang-troubleshooting (root cause) |
| Debug a panic or unexpected behavior | golang-troubleshooting |
golang-safety, golang-benchmark (if perf-related) |
| Monitor in production | golang-observability |
golang-performance (if SLO breach) |
| Audit security vulnerabilities | golang-security |
golang-safety, golang-lint |
| Review formatting and style | golang-code-style |
golang-naming, golang-lint |
| Refactor or restructure existing code | golang-refactoring |
golang-naming, golang-code-style, golang-project-layout |
| Configure golangci-lint | golang-lint |
golang-code-style |
| Write godoc / README / CHANGELOG | golang-documentation |
golang-naming |
| Set up a new project structure | golang-project-layout |
golang-design-patterns, golang-dependency-injection, golang-lint |
| Set up CI/CD pipeline | golang-continuous-integration |
golang-lint, golang-security |
| Choose a library | golang-popular-libraries |
relevant library-specific skill |
| Look up a package's docs, versions, importers, or CVEs | golang-pkg-go-dev |
golang-dependency-management |
| Navigate, diagnose, or refactor local code (definitions, references, rename) | golang-gopls |
— |
| Adopt new Go language features | golang-modernize |
golang-lint |
| Use samber/lo (slice/map helpers) | golang-samber-lo |
golang-data-structures, golang-performance |
| Use samber/oops (structured errors) | golang-samber-oops |
golang-error-handling |
| Use log/slog | golang-samber-slog |
golang-observability, golang-error-handling |
| Use dependency injection | golang-dependency-injection |
golang-google-wire or golang-uber-dig or golang-uber-fx or golang-samber-do |
What ships with it
4 files 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.
- 8d ago Changed ec364f51bec9
- 10d ago Changed 3ab7e9a5d9bf
- 13d ago First seen · 161 lines · 185 tokens per session scan A 2a2945d4429f
golang-how-to is a skill published in the GitHub repository samber/cc-skills-golang (3,232 stars, last pushed 5d ago), licensed MIT. It adds 185 tokens to every session and 4,210 once invoked, about $0.0009 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
stack-trace-go-probe
Internal helper for meta-stack-trace-investigator. Use when a Go panic or stack trace needs Go-specific nil/error checks, go test reproducer guidance, and patch targets.
site-launch-checklist
Pre-launch checklist for shipping a new website or web app. Scope: analytics (GA4, PostHog, Google Search Console, Ahrefs), DNS, TLS and backups, legal and CNIL/GDPR compliance, security headers, SEO and GEO (robots.txt, sitemaps, llms.txt, hreflang, schema markup, keyword research), copywriting voice via TONE.md and…
copywriting-hooks
Writes opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, newsletters, essays. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including…
chrome-extension
Build Chrome extensions with Manifest V3. Use this skill whenever the user mentions Chrome extension, browser extension, manifest.json, content script, service worker (in extension context), popup, side panel, chrome.runtime, chrome.tabs, chrome.storage, chrome.scripting, or any Chrome extension API. Also trigger when…
copywriting-prose-creator
Codifies how a person or brand writes — lexicon, syntax, rhythm, structure, signature moves — into a PROSE.md guide, independent of emotional tone. Builds from SOUL.md and TONE.md, ports a guide to another channel, or reverse-engineers prose patterns from a corpus. Trigger on PROSE.md, writing style guide, prose…
deep-research
Deep research on any topic — broad parallel web searches, multi-source validation, confidence tracking, and a cited Markdown report. Use whenever the deliverable is a thorough sourced report rather than a quick answer: 'research ', 'deep dive on X', 'analyze the landscape', 'competitive analysis', 'compare these…