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 julianobarbosa/claude-code-skills --skill writing-gogit clone --depth 1 https://github.com/julianobarbosa/claude-code-skillsWrote 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/julianobarbosa/claude-code-skills/writing-go)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/writing-go"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/writing-go/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/julianobarbosa/claude-code-skills/writing-go"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/writing-go.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 | $0.00048 | $0.00791 |
| Opus 5 | $0.00024 | $0.00396 |
| Sonnet 5 | $0.00010 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
writing-go 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Development (1.25+)
Core Principles
- Stdlib first: External deps only when justified
- Concrete types: Define interfaces at consumer, return structs
- Composition: Over inheritance, always
- Fail fast: Clear errors with context
- Simple: The obvious solution is usually correct
Quick Patterns
Error Handling
if err := doThing(); err != nil {
return fmt.Errorf("do thing: %w", err)
}
Struct with Options
type Server struct {
addr string
timeout time.Duration
}
func NewServer(addr string, opts ...Option) *Server {
s := &Server{addr: addr, timeout: 30 * time.Second}
for _, opt := range opts {
opt(s)
}
return s
}
Table-Driven Tests
tests := []struct {
name string
input string
want string
wantErr bool
}{
{"valid", "hello", "HELLO", false},
{"empty", "", "", true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
got, err := Process(tt.input)
if tt.wantErr {
require.Error(t, err)
return
}
require.NoError(t, err)
assert.Equal(t, tt.want, got)
})
}
Go 1.25 Features
- testing/synctest: Deterministic concurrent testing with simulated clock
- encoding/json/v2: Experimental, 3-10x faster (GOEXPERIMENT=jsonv2)
- runtime/trace.FlightRecorder: Production trace capture on-demand
- Container-aware GOMAXPROCS: Auto-detects cgroup limits
- GreenTea GC: Experimental, lower latency (GOEXPERIMENT=greenteagc)
References
- PATTERNS.md - Detailed code patterns
- TESTING.md - Testing strategies with testify/mockery
- CLI.md - CLI application patterns
Tooling
go build ./... # Build
go test -race ./... # Test with race detector
golangci-lint run # Lint
mockery --all # Generate mocks
Gotchas
nilchannel sends/receives block forever; closed channel receives return zero value immediately —selectwith a nil channel case disables that case, useful pattern but easy to do accidentally.defercaptures arguments at the call site, not at execution —defer fmt.Println(time.Now())captures NOW, not the deferred time.- Pre-Go 1.22 for-loop variable capture closures over ONE variable across all iterations — the goroutine-in-loop bug. Go 1.22 changed semantics; old habits create subtle bugs in mixed-version code.
errors.IswalksUnwrap()chains, BUT if a wrapped error implementsIs(target error) boolitself, that custom Is wins over walking — confusing when migrating from xerrors.sync.Poolitems can be GC'd betweenGetand the nextPut— never rely on a Pool to retain state.
What ships with it
3 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 First seen · 101 lines · 48 tokens per session scan A 532e80068687
writing-go is a skill published in the GitHub repository julianobarbosa/claude-code-skills (10 stars, last pushed 16d ago), licensed MIT. It adds 48 tokens to every session and 791 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 2026-09-03.
Other skills, from other repositories
timeouts-and-async
Make Ginkgo specs interruptible and test asynchronous behavior — SpecContext/context.Context cancellable nodes, NodeTimeout/SpecTimeout/GracePeriod, the --timeout flag, Abort and SIGINT behavior, Gomega Eventually/Consistently (the func(g Gomega) form, .WithContext), and the defer GinkgoRecover() rule for goroutines.…
setup
Wire Ginkgo into a Go package — install the ginkgo CLI and Ginkgo+Gomega, ginkgo bootstrap to generate the suitetest.go (TestXxx/RegisterFailHandler(Fail)/RunSpecs), the package xxxtest convention, dot-import alternatives (aliased import, dsl/ subpackages, --nodot), ginkgo generate, and testing.T interop via…
golang-testing
Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI…
overview
The Ginkgo mental model for writing Go tests — the one idea that explains everything (Ginkgo builds a spec tree at construction time, then runs it) and its consequences for how you write specs, plus spec independence and the node taxonomy. Use this first when you start working with Ginkgo in a project, or to decide…
golang-stretchr-testify
Comprehensive guide to stretchr/testify for Golang testing. Covers assert, require, mock, and suite packages in depth. Use when writing tests with testify, creating mocks, setting up test suites, or choosing between assert and require. Covers testify assertions, mock expectations, argument matchers, call verification…
assertions
Write correct synchronous Gomega assertions — Expect/Ω notation, the To/NotTo/ToNot/Should/ShouldNot equivalences, the multi-return error idiom, Succeed vs HaveOccurred, the .Error() chaining form, annotating assertions (format-string and func()string), tuning failure output via the format subpackage…