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 daibang123a/golang-agent-skills --skill go-best-practicesgit clone --depth 1 https://github.com/daibang123a/golang-agent-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/daibang123a/golang-agent-skills/go-best-practices)<a href="https://agentmods.dev/skills/daibang123a/golang-agent-skills/go-best-practices"><img src="https://agentmods.dev/badge/skills/daibang123a/golang-agent-skills/go-best-practices/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/daibang123a/golang-agent-skills/go-best-practices"><img src="https://agentmods.dev/badge/skills/daibang123a/golang-agent-skills/go-best-practices.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 | $0.00076 | $0.02425 |
| Opus 5.5 | $0.00030 | $0.00970 |
| Sonnet 5.5 | $0.00015 | $0.00485 |
| Haiku 4.5 | $0.00008 | $0.00243 |
Grade A, and why
go-best-practices 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 2mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Best Practices
Performance optimization and idiomatic Go coding guidelines. 50+ rules across 9 categories, prioritized by impact.
How It Works
- Agent receives Go code to write or review
- Agent loads this skill and applies relevant rules by category
- Rules are applied in priority order: Critical → High → Medium → Low
- Agent provides specific, actionable feedback with code examples
Rules
1. Memory & Allocation (Critical)
| # | Rule | Description |
|---|---|---|
| M1 | Pre-allocate slices | Use make([]T, 0, n) when size is known or estimable. Reduces GC pressure from repeated growth. |
| M2 | Avoid unnecessary pointers | Value types on the stack are cheaper than heap-allocated pointers. Only use pointers when mutation or nil semantics are needed. |
| M3 | Use sync.Pool for hot-path allocations | Pool frequently allocated objects (buffers, structs) in performance-critical paths. Always reset before returning to pool. |
| M4 | Prefer strings.Builder for concatenation | Never use + in loops. strings.Builder avoids intermediate allocations. |
| M5 | Avoid []byte ↔ string conversions | Each conversion allocates. Use strings.Builder or work consistently with one type. |
| M6 | Use appropriate map sizing | make(map[K]V, n) with expected capacity avoids rehashing. Maps never shrink — consider periodic recreation for long-lived maps. |
| M7 | Watch for slice memory leaks | Slicing a large slice keeps the full backing array alive. Copy to a new slice if retaining a small portion. |
| M8 | Prefer value receivers for small structs | Structs ≤ 3 words are cheaper to copy than to indirect through a pointer. |
2. Error Handling (Critical)
| # | Rule | Description |
|---|---|---|
| E1 | Always handle errors | Never use _ to discard errors unless explicitly justified with a comment. |
| E2 | Wrap errors with context | Use fmt.Errorf("operation failed: %w", err) to add context while preserving the error chain. |
| E3 | Define sentinel errors as package-level vars | var ErrNotFound = errors.New("not found"). Callers use errors.Is(). |
| E4 | Define error types for structured info | Use custom types implementing error when callers need to extract fields. Callers use errors.As(). |
| E5 | Don't panic in library code | Libraries should return errors. Panics are only acceptable for truly unrecoverable programmer errors. |
| E6 | Use errors.Is/As, not == or type assertions | Direct comparison breaks when errors are wrapped. Always use the errors package functions. |
| E7 | Don't log and return | Either log the error and handle it, or wrap and return it. Never both — it creates duplicate log entries. |
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.
- 2mo ago First seen · 140 lines · 76 tokens per session scan A 74d0e3879787
go-best-practices is a skill published in the GitHub repository daibang123a/golang-agent-skills (2 stars, last pushed 8mo ago), licensed MIT. It adds 76 tokens to every session and 2,425 once invoked, about $0.0003 per session on Opus 5.5. 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.
go-best-practices compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| go-best-practicesdaibang123a/golang-agent-skills | Skill | 2 | 8mo ago | MIT | A | 76 | Claude Code, Codex |
| golang-testingaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 37 | Claude Code, Kiro |
| golang-patternsaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 45 | Claude Code, Kiro |
| golang-testingsamber/cc-skills-golang | Skill | 3.8k | 5d ago | MIT | A | 115 | Claude Code |
| golang-uber-fxsamber/cc-skills-golang | Skill | 3.8k | 5d ago | MIT | A | 122 | Claude Code |
| golang-samber-oopssamber/cc-skills-golang | Skill | 3.8k | 5d ago | MIT | A | 74 | Claude Code |
| ax-go-agent-optimizeax-llm/ax | Skill | 3.0k | 3d ago | Apache-2.0 | A | 51 | Claude Code, Codex |