gopher

gopher is a skill for Claude Code, Codex from gemyago/atlacp. It costs 43 tokens per session (1,098 once invoked), scanned A, original, MIT.

A portable guide to Go coding and testing practices, including interfaces, error handling, structured logging, tests, and a test-driven development mindset. TDD means writing tests as part of designing and building code.

In plain words
What is it for?
Writing or reviewing Go code, designing testable components, handling errors, adding logs, and creating or improving tests.
Why use it?
It gives consistent Go habits while telling the agent to follow each repository’s own versions, layout, commands, and security rules.

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/gemyago/atlacp/gopher
Any agent
npx skills add gemyago/atlacp --skill gopher
Clone the repo
git clone --depth 1 https://github.com/gemyago/atlacp

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 gopher

README.md
[![agentmods](https://agentmods.dev/badge/skills/gemyago/atlacp/gopher.svg)](https://agentmods.dev/skills/gemyago/atlacp/gopher)
Your own site
<a href="https://agentmods.dev/skills/gemyago/atlacp/gopher"><img src="https://agentmods.dev/badge/skills/gemyago/atlacp/gopher.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,098 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 $0.00043 $0.01098
Opus 5 $0.00022 $0.00549
Sonnet 5 $0.00009 $0.00220
Haiku 4.5 $0.00004 $0.00110

Measured 5d ago against content hash d2d8229881e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gopher 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.

.agent/skills/gopher/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gopher — Go coding and testing (generic)

Use with project docs. This skill is not a substitute for the repository’s own rules. Always read the nearest AGENTS.md (or your project’s equivalent: CONTRIBUTING.md, team wiki, Cursor rules) for:

  • Go / toolchain versions and how they are pinned
  • Repo layout, module boundaries, and where application code lives
  • How to run lint and tests, and what “done” means before you report back
  • Codegen (OpenAPI/protobuf/sqlc/etc.), mock generation, and migration commands
  • Security and compliance expectations for this codebase
  • Framework-specific rules (ORM, HTTP routers, DI, specialized SDKs, etc.)

Nearest project instructions win when they conflict with anything below.


Go coding guide (language-level)

Key considerations

  • Accept interfaces, return structs canonical way to structure code:
    • Dependencies (services, repos, clients or any other components) SHELL be accepted as consumer defined interfaces (testability, boundaries).
    • Return concrete types (structs) from constructors.
  • Define interfaces next to the consumer (same file by default); split only when size or reuse demands it.
  • Use log/slog (or the project’s logging facade) as an injected dependency — avoid global loggers unless the project already standardized on them.
  • Wrap errors: fmt.Errorf("context: %w", err) (or the project’s error helpers).
  • Methods with more than 3 arguments (context does not count) is a warning sign. Use params struct instead.
  • Names such as "tools", "helpers", "utils" e.t.c are banned. Use descriptive names instead.
  • Prefer functional options for optional constructor parameters: a type FooOption func(*Foo) (or *fooConfig), WithBar(...) functions that set fields, and NewFoo(opts ...FooOption) applying them in order. Avoid a separate NewFooWithOpts when the zero-arg NewFoo() case is the default.

Testing style and patterns (from the coding guide)

Read the full file on GitHub · 79 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 · 79 lines · 43 tokens per session scan A d2d8229881e7

Subscribe to this mod's changes

gopher is a skill published in the GitHub repository gemyago/atlacp (7 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,098 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.