go-conventions

go-conventions is a skill for Claude Code, Codex from andr-ca/agentharness. It costs 48 tokens per session (861 once invoked), scanned A, original, MIT.

A set of conventions for writing and reviewing Go code, covering names, errors, interfaces, and safe use of goroutines.

In plain words
What is it for?
It guides naming exported and private code, wrapping errors, defining interfaces, choosing method receivers, and writing safer concurrent code.
Why use it?
It helps avoid unclear code and common Go problems such as lost error context, goroutine leaks, deferred work inside loops, and writes to nil maps.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/andr-ca/agentharness/go-conventions
Any agent
npx skills add andr-ca/agentharness --skill go-conventions
Clone the repo
git clone --depth 1 https://github.com/andr-ca/agentharness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for go-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/andr-ca/agentharness/go-conventions.svg)](https://agentmods.dev/skills/andr-ca/agentharness/go-conventions)
Your own site
<a href="https://agentmods.dev/skills/andr-ca/agentharness/go-conventions"><img src="https://agentmods.dev/badge/skills/andr-ca/agentharness/go-conventions.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 861 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00048 $0.00861
Opus 5 $0.00024 $0.00430
Sonnet 5 $0.00010 $0.00172
Haiku 4.5 $0.00005 $0.00086

Measured 5d ago against content hash 35070722f23c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

go-conventions 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 5d 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.

.claude/skills/go-conventions/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Go Conventions

This file is self-contained for day-to-day use. Deeper reference (needs the full harness checkout): languages/go/CONVENTIONS.md (full examples including godoc comments, context-first concurrency, and table-driven tests).

Naming

  • Unexported: camelCase. Exported: PascalCase.
  • Interfaces: singular, behavior-describing name (Reader, Storer, UserRepository — not IUserRepository).
  • Error sentinels: Err prefix (ErrNotFound, ErrTimeout).
  • Receiver: one or two letters, the type's initials (u *User, not user *User). Keep consistent across all methods of a type.

Errors: wrap with context, return early

// Wrap to preserve the stack — don't swallow context
if err != nil {
    return fmt.Errorf("getUserByID %q: %w", id, err)
}

// Return early — avoid deep nesting
func process(ctx context.Context, id string) error {
    user, err := repo.Find(ctx, id)
    if err != nil {
        return fmt.Errorf("process: find user: %w", err)
    }
    // ... rest of the logic at the same indent level
}

Interfaces: define at the point of use

Declare the interface in the package that uses it, not the package that implements it. A concrete type's package need not know about the interface — io.Reader doesn't live in the os package, and UserRepository should live in the handler/service that calls it, not in the postgres package that provides one.

Pitfalls to catch in review

// Goroutine leak — if nothing reads from result, the goroutine
// blocks forever on the send and is never garbage-collected
go func() {
    result <- compute()  // will block if nobody reads result
}()

// Defer in loop executes at *function* return, not loop iteration
for _, f := range files {
    defer f.Close()  // WRONG — all defers run when function exits
    // RIGHT: use an inner function or close explicitly at end of loop
}

// Write to a nil map panics at runtime
var m map[string]int
m["key"] = 1  // panic: assignment to entry in nil map
// RIGHT: initialize first (use = not :=, m is already declared)
m = make(map[string]int)

// Shadowing err in short variable declaration inside a block
result, err := doSomething()
if err == nil {
    data, err := doAnotherThing()  // this `err` is a new variable
    _ = data
}
// The outer `err` is unchanged; use `=` for the inner one if intended

Read the full file on GitHub · 106 lines

Changes

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.

  1. 5d ago First seen · 106 lines · 48 tokens per session scan A 35070722f23c

Subscribe to this mod's changes

go-conventions is a skill published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 861 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 2026-08-31.

Related

Other skills, from other repositories

modern-cli-design

Principles for building Unix-composable command-line tools in Go: stdout/stderr discipline, JSON and plain output modes, semantic exit codes, noun-verb commands, structured errors. Use when designing, building, or reviewing CLIs.

saski/arnesto · 51 tokens

go-code-reduce

Find and, when authorized, apply maintainable Go code reductions. Use when a user asks to reduce Go lines, boilerplate, duplication, or obsolete idioms without changing behavior; not for general implementation or style review.

yarlson/yarstack · 49 tokens

neneko-code-taste

Use when implementing or reviewing Go changes that should match tRPC-Agent-Go's code taste: minimal compatible diffs, consumer-oriented APIs, explicit ownership, and contract-level tests. Do not use for generic Go formatting-only requests.

XnLemon/Neneko-skill · 51 tokens

golang-testing

Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.

affaan-m/ECC · 37 tokens

golang-patterns

Go-specific design patterns and best practices including functional options, small interfaces, dependency injection, concurrency patterns, error handling, and package organization. Use when working with Go code to apply idiomatic Go patterns.

affaan-m/ECC · 45 tokens

ast-grep

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…

JanDeDobbeleer/oh-my-posh · 80 tokens