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 sgaunet/claude-plugins --skill go-blackboxgit clone --depth 1 https://github.com/sgaunet/claude-pluginsWrote 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/sgaunet/claude-plugins/go-blackbox)<a href="https://agentmods.dev/skills/sgaunet/claude-plugins/go-blackbox"><img src="https://agentmods.dev/badge/skills/sgaunet/claude-plugins/go-blackbox.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 5.1 | $0.00034 | $0.01299 |
| Opus 5 | $0.00017 | $0.00649 |
| Sonnet 5 | $0.00007 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
go-blackbox 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 7d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Go Black Box Test Enforcement
Detect Go test files using white box testing (same package name) and propose conversion to black box testing (package foo_test). Creates export_test.go bridge files when internal symbols need external test access.
When to Use
- Creating new test files (enforce black box from the start)
- Reviewing existing test files in a Go project
- User asks to audit or improve test quality
- The golang-pro agent encounters
*_test.gofiles during implementation
Prerequisites
- go.mod exists: Abort if missing.
- Go source files exist: At least one
.gofile and one*_test.gofile to analyze.
Workflow: Detect White Box Tests
Step 1: Classify Test Files with go list
go list already reports the in-package/external split per package, and honours
build constraints. Use it rather than globbing:
go list -f '{{.ImportPath}} {{.Name}} white={{.TestGoFiles}} black={{.XTestGoFiles}}' ./...
| Field | Package clause | Classification |
|---|---|---|
TestGoFiles |
package foo |
White box — candidate for conversion |
XTestGoFiles |
package foo_test |
Black box — already correct |
Two rules when reading the output:
- Drop
export_test.gofrom the white box set. It is a bridge file and belongs to the source package by design, so it is never a conversion candidate. - A package can legitimately hold both. Seeing entries in
TestGoFilesandXTestGoFilesfor the same package is normal, not a defect.
Why not Glob **/*_test.go and read package lines: a test file behind a
constraint like //go:build linux is matched by Glob on any OS but correctly
excluded by go list, so the manual approach both over- and under-reports. go list also names the source package directly, removing the need to read sibling
non-test files to infer it.
Step 2: Check for export_test.go
For each directory containing test files, check whether an export_test.go already exists.
Step 3: Report Findings
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.
- 7d ago First seen · 137 lines · 34 tokens per session scan A d47ec8b02ce9
go-blackbox is a skill published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 1,299 once invoked, about $0.0002 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
dotnet-test
This skill should be used when running .NET tests selectively with a build-first, test-targeted workflow. Use it for running tests with xUnit focus.
dotnet-verify
This skill should be used when working with Verify snapshot tests in .NET projects. Use when updating verified snapshots after intentional code changes, accepting new snapshots, discovering verify tests, or troubleshooting snapshot mismatches. Trigger phrases include "verify tests", "update snapshots", "accept…
testing-go
Writes tests following TDD (using go test, testify, and rapid) best practices. Use when writing unit tests, integration tests, or table-driven tests in Go.
testing-python
Writes tests following TDD Red-Green-Refactor (pytest + Hypothesis). Tests behavior, not implementation. Use when writing unit tests, integration tests, or property tests.
testing-rust
Writes tests following TDD (using cargo test, proptest, and insta) best practices. Use when writing unit tests, integration tests, or property-based tests in Rust.
testing-typescript
Writes tests following TDD (using vitest and @testing-library/react) best practices. Use when writing unit tests, integration tests, or component tests in TypeScript.