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 saisudhir14/claude-skills --skill go-code-reviewgit clone --depth 1 https://github.com/saisudhir14/claude-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/saisudhir14/claude-skills/go-code-review)<a href="https://agentmods.dev/skills/saisudhir14/claude-skills/go-code-review"><img src="https://agentmods.dev/badge/skills/saisudhir14/claude-skills/go-code-review/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/saisudhir14/claude-skills/go-code-review"><img src="https://agentmods.dev/badge/skills/saisudhir14/claude-skills/go-code-review.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 | $0.00044 | $0.00844 |
| Opus 5.5 | $0.00018 | $0.00338 |
| Sonnet 5.5 | $0.00009 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
go-code-review 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Code Review Checklist
Quick-reference checklist for reviewing Go code. Each item links to deeper guidance in the parent skill.
Naming
- MixedCaps used (no underscores)
- Initialisms are consistent case (URL, ID, HTTP)
- Variable names match scope (short for local, descriptive for global)
- Receiver names are 1-2 letters, consistent across methods
- Package names are lowercase single words, no util/common/misc
- No name repetition (package.Method, not package.PackageMethod)
Error Handling
- Errors returned, not panicked (production code)
- Error wrapping uses
%wor%vappropriately - Error context is succinct (no "failed to" chains)
- Errors handled once (not logged AND returned)
- Error strings are lowercase, no trailing punctuation
- Happy path at minimal indentation (error-first)
- Sentinel errors use
Errprefix, error types useErrorsuffix
Concurrency
- Channel buffers are 0 or 1 (or justified)
- Goroutine lifetimes are documented
- errgroup used for error-returning goroutines
- Functions are synchronous unless concurrency is essential
- Mutexes are zero-value, unexported, not embedded in public structs
- Typed atomics used (Go 1.19+)
Testing
- Table-driven tests with named subtests
- Subtests run in parallel where safe
- go-cmp used for struct comparisons
- Failure messages include input, got, want
- t.Fatal for setup errors, t.Error for test assertions
- Interfaces defined in consumer packages
Imports
- Three groups: stdlib, external, internal
- No unnecessary renames
- No dot imports (except circular dep tests)
- Blank imports only in main/tests
Structs
- Field names used in initialization (no positional)
- Zero value fields omitted
- Types not embedded in public structs
- JSON field tags on marshaled structs
Slices and Maps
- Nil slices preferred over empty slices
- Copied at boundaries to prevent mutation
- Capacity preallocated when size is known
- Standard library slices/maps packages used
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 · 109 lines · 44 tokens per session scan A 8583eb642162
go-code-review is a skill published in the GitHub repository saisudhir14/claude-skills (8 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 844 once invoked, about $0.0002 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-code-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| go-code-reviewsaisudhir14/claude-skills | Skill | 8 | 4mo ago | MIT | A | 44 | Claude Code, Codex |
| pr-to-go-lintergithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 22 | Claude Code, Codex |
| golang-refactoringsamber/cc-skills-golang | Skill | 3.8k | 5d ago | MIT | A | 220 | Claude Code |
| go-spec-reviewerspf13/go-skills | Skill | 697 | yesterday | MIT | A | 99 | Claude Code |
| design-reviewdimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 30 | Claude Code, Codex |
| agents-mddimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 138 | Claude Code, Codex |
| ring:verifying-codeLerianStudio/ring | Skill | 218 | 6d ago | Apache-2.0 | A | 101 | Cursor |