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 madflojo/go-style-agent-skill --skill go-style-guidegit clone --depth 1 https://github.com/madflojo/go-style-agent-skillWrote 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/madflojo/go-style-agent-skill/go-style-guide)<a href="https://agentmods.dev/skills/madflojo/go-style-agent-skill/go-style-guide"><img src="https://agentmods.dev/badge/skills/madflojo/go-style-agent-skill/go-style-guide/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/madflojo/go-style-agent-skill/go-style-guide"><img src="https://agentmods.dev/badge/skills/madflojo/go-style-agent-skill/go-style-guide.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 | $0.00077 | $0.01879 |
| Opus 5 | $0.00039 | $0.00940 |
| Sonnet 5 | $0.00015 | $0.00376 |
| Haiku 4.5 | $0.00008 | $0.00188 |
Grade A, and why
go-style-guide 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 11d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go (Golang) Style Guide Skill
This skill defines practical Go engineering conventions for humans, coding agents, and production-ready systems.
Use this skill whenever you are working with Go: new code, refactors, reviews, architecture decisions, package design, or test strategy.
TL;DR
- Design for testability first; inject dependencies and keep logic pure.
- Prefer
Configin -> concrete struct out; validate, default, and document important runtime knobs. - Errors are contracts: use sentinels for durable branching; wrap the rest with
%worerrors.Join. - Keep packages reusable: no hidden globals, no default logging, no surprise side effects.
- Prefer the standard library before adding dependencies; third-party packages must earn their weight through meaningful, maintained, adopted abstraction.
- Coverage is a signal, not proof; test edge cases and misuse paths, not just happy paths.
- Follow "accept interfaces, return structs"; consumers usually define interfaces, shared contract packages are a special case.
- Keep
main.gothin; follow existing repo layout conventions rather than forcing one directory shape. - Benchmark hot paths before claiming wins, and run concurrency code with
-race. - Maintain contracts such as function signatures, config shape, error behavior, and doc comments; they are as important as the code itself.
House Style Disclaimer
This is intentionally opinionated. It favors consistency and long-term maintainability over accommodating every Go style preference. If the target repo has clear local conventions, those conventions usually win.
Compatibility
Examples assume modern Go and use standard-library features such as
errors.Join and log/slog. Apply the guide within the constraints of the
target repository's supported Go version.
Execution Protocol
Follow this workflow when using the skill for implementation work:
- Inspect the repository first. Read existing package layout, constructors, tests, and error conventions before proposing new APIs or moving files.
What ships with it
10 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.
- references/BENCHMARKS.md 6.6 KB
- references/CONCURRENCY.md 17 KB
- references/CONFIG.md 9.5 KB
- references/DOCUMENTATION.md 11 KB
- references/ERRORS.md 6.4 KB
- references/INTERFACES.md 7.8 KB
- references/LAYOUT.md 12 KB
- references/LOGGING.md 9.6 KB
- references/REVIEW-CHECKLIST.md 9.1 KB
- references/TESTING.md 15 KB
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.
- 11d ago First seen · 184 lines · 77 tokens per session scan A c8506593d73c
go-style-guide is a skill published in the GitHub repository madflojo/go-style-agent-skill (35 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 1,879 once invoked, about $0.0004 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
golang-refactoring
Golang refactoring — safe, at-scale restructuring of existing Go code: a coverage-adaptive safety net, behavior-preserving transforms (gopls Rename/Extract, gofmt -r, gopatch), the Fowler catalog mapped to Go, breaking import cycles, and small stacked PRs. Apply when a function or type has grown too large, a code…
sapcc-review
Gold-standard SAP CC Go code review: 10 parallel domain specialists.
go-concurrency-safety
L1 supplement - audits Go-specific concurrency hazards in node client code: map iteration non-determinism, goroutine leaks, mutex ordering, panic boundaries, context cancellation.
design-review
Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension and provides actionable fixes.
agents-md
Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects. Use this skill whenever the user asks to create, scaffold, bootstrap, update, or review an AGENTS.md (or agent-instructions, CLAUDE.md, repo guide for agents) file in a codebase. Also trigger when the user says "add AGENTS.md", "make this repo…
sapcc-audit
Full-repo SAP CC Go compliance audit against review standards.