Use Modern GoSAFE
Help AI coding agents write modern Go
Overview
Help AI coding agents write modern Go
82698c4db577OBSERVED · 2026-10-20What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: use-modern-go description: Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes. --- # Modern Go Guidelines CLI Always write modern, idiomatic Go code. Use the Modern Go Guidelines CLI as the source of truth for modern Go idioms that may be newer than your knowledge cutoff. Command: - Linux or macOS: `sh "<skill-dir>/scripts/run-tool.sh"` - Windows PowerShell: `& '<skill-dir>\scripts\run-tool.ps1'` First run and approvals: On first use, the wrapper installs the Modern Go Guidelines CLI in a local cache directory. Subcommands: - `list` - `explain` Before editing Go code: 1. Call the wrapper's `list` subcommand for the relevant Go file. Prefer passing the file you are about to edit: ```sh sh "<skill-dir>/scripts/run-tool.sh" list --file-path path/to/file.go ``` On Windows, use the PowerShell wrapper with the same arguments. The CLI resolves the applicable Go version from go.mod, go.work, the local Go toolchain, or an explicit override. 2. If the target Go version is already known, you may pass it directly: ```sh sh "<skill-dir>/scripts/run-tool.sh" list --go-version 1.24 ``` 3. Read the complete list output before deciding which guidelines apply. The list output is ordered newest first. Read the full output because older supported guidelines may still apply. Do not pipe the output through head, tail, grep, sed, or any other truncating/filtering command. Important guidelines may otherwise be missed. 4. Treat returned guidelines as authoritative for modern Go style choices in code you are editing. If a guideline applies, follow it even when nearby code or repository convention uses an older pattern. Skip it only when it would not compile, would change behavior, or clearly does not match the edited code. Before skipping a returned guideline that seems relevant, call the wrapper's `explain` subcommand for that guideline ID. Call `explain` only when a specific guideline may apply and you need the detailed explanation or examples. Request only the guideline IDs you intend to evaluate or apply: ```sh sh "<skill-dir>/scripts/run-tool.sh" explain sync_waitgroup_go ``` Multiple guideline IDs may be requested as positional arguments: ```sh sh "<skill-dir>/scripts/run-tool.sh" explain atomic_types errors_as_type ``` Do not call `explain` without guideline IDs. Use `list` first to discover the short guideline list for the target Go version, then call `explain` for the specific returned IDs that need more context.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
82698c4db577full audit observations/trust-audit/skill/jetbrains__use-modern-go.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-20 | 82698c4db577 | SAFE | B | 89 | first audit |
Questions
What does the use-modern-go — jetbrains/go-modern-guidelines skill do?
Help AI coding agents write modern Go
Is use-modern-go — jetbrains/go-modern-guidelines safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can use-modern-go — jetbrains/go-modern-guidelines access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (82698c4db577), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.
Add this badge to your README
Shows this page's audit result and links back to it. It updates when the audit does.
[](https://modelsatlas.com/skills/jetbrains/use-modern-go/)
Not your listing, or something out of date? Claim or update your listing.