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 agentmods add commands/mfmezger/ai_agent_dotfiles/go-engineeringgit clone --depth 1 https://github.com/mfmezger/ai_agent_dotfilesWrote 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/commands/mfmezger/ai_agent_dotfiles/go-engineering)<a href="https://agentmods.dev/commands/mfmezger/ai_agent_dotfiles/go-engineering"><img src="https://agentmods.dev/badge/commands/mfmezger/ai_agent_dotfiles/go-engineering.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.00832 |
| Opus 5 | $0.00046 | $0.00416 |
| Sonnet 5 | $0.00018 | $0.00166 |
| Haiku 4.5 | $0.00009 | $0.00083 |
Grade A, and why
go-engineering 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Engineering
Produce Go that is small in surface area, explicit in behavior, and easy to read under review. Prefer straightforward package boundaries, concrete types first, small interfaces where they help callers, explicit error handling, and concurrency that can be reasoned about.
Workflow
- Identify the package boundary. Library: optimize for small exports, concrete behavior, and compatibility. Application: optimize for operability, wiring clarity, and cancellation-aware execution.
- Model the package API before adding helpers. Keep exported identifiers minimal and make zero values useful when practical.
- Choose concrete types first. Introduce interfaces where consumers benefit, not as a reflex.
- Design error flow early.
Wrap with context, support
errors.Isanderrors.As, and keep sentinel errors narrow. - Add concurrency only where it simplifies latency or throughput. Cancellation, shutdown, ownership, and goroutine lifetime must be explicit.
- Verify before finalizing.
Run
gofmt,go test ./..., andgo vet ./...when appropriate. Addgo test -race ./...for concurrency-sensitive code. Keep examples and benchmarks honest.
Load References By Need
| Need | Reference |
|---|---|
| Package layout, modules, exported API shape, CLI/app structure | references/workflow.md |
| Errors, wrapping, sentinels, concrete types vs interfaces | references/api-and-errors.md |
| Concurrency, channels, contexts, goroutines, shutdown | references/concurrency.md |
| Testing, table tests, fuzzing, benchmarks, temp dirs | references/testing-and-quality.md |
| Performance, allocations, slices, maps, common footguns | references/performance-and-footguns.md |
Default Standards
- Keep packages focused and exports intentional.
- Start with concrete types; accept interfaces when they improve the consuming code.
- Pass
context.Contextexplicitly for request-scoped or cancelable work. - Return errors, wrap them with context, and avoid panic for ordinary failures.
- Prefer simple loops and data flow over abstraction-heavy “framework” patterns.
- Keep goroutine ownership clear. Every goroutine should have a reason to exit.
- Make the zero value useful when practical and not misleading.
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.
- 5d ago First seen · 65 lines · 92 tokens per session scan A 0adbc625dce4
go-engineering is a command published in the GitHub repository mfmezger/ai_agent_dotfiles (5 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 832 once invoked, about $0.0005 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.
Other commands, from other repositories
cli-patterns
Reference patterns for implementing CLI commands in internal/cli/.
create-go-project
Create a new Go web project with Templ, HTMX, Tailwind, and sqlc.
golang-test-review
Use when reviewing Go test code (new or changed test.go files, test harnesses, fixtures, or test tooling) for a Go-test-expert pass — behavior-over-surface, determinism, parallel-safety, build-tag correctness, and harness reuse. Complements the general code-reviewer with test-specific rigor.
add-test-fixture-and-go-test-for-langgraph-js-rule
Workflow command scaffold for add-test-fixture-and-go-test-for-langgraph-js-rule in shingan.
go-test
强制执行 Go 的测试驱动开发（TDD）工作流。先编写表驱动测试（Table-Driven Tests），然后进行实现。使用 go test -cover 验证 80% 以上的覆盖率。.
go-workflow-engineer
Command "go-workflow-engineer" from ready-to-release/eac, covering workflow engineer, process and example usage.