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 skills/gollem-dev/gollem/test-with-gtnpx skills add gollem-dev/gollem --skill test-with-gtgit clone --depth 1 https://github.com/gollem-dev/gollemWrote 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/gollem-dev/gollem/test-with-gt)<a href="https://agentmods.dev/skills/gollem-dev/gollem/test-with-gt"><img src="https://agentmods.dev/badge/skills/gollem-dev/gollem/test-with-gt.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 | $0.00035 | $0.00634 |
| Opus 5 | $0.00017 | $0.00317 |
| Sonnet 5 | $0.00007 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
test-with-gt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Writing Tests with gt
When writing Go test code, use the gt library for type-safe assertions.
Step 1: Locate gt documentation
First, find where gt is installed and read its documentation:
GT_DIR=$(go list -m -f '{{.Dir}}' github.com/m-mizutani/gt 2>/dev/null)
If gt is available, read the relevant documentation from $GT_DIR/docs/:
docs/README.md- Overview and quick referencedocs/types/*.md- Detailed documentation for each test typedocs/patterns/*.md- Common patterns (method chaining, Required, Describe)
Step 2: Choose the right test type
| Data Type | Use | NOT |
|---|---|---|
[]T (slice) |
gt.Array(t, arr).Length(3) |
gt.Value(t, len(arr)).Equal(3) |
string |
gt.String(t, s).Contains("x") |
gt.Bool(t, strings.Contains(s, "x")).True() |
error |
gt.NoError(t, err) |
gt.Value(t, err).Nil() |
int, float, etc. |
gt.Number(t, n).Greater(5) |
gt.Bool(t, n > 5).True() |
map[K]V |
gt.Map(t, m).HasKey("k") |
manual check with gt.Bool |
bool |
gt.Bool(t, b).True() |
gt.Value(t, b).Equal(true) |
Step 3: Apply common patterns
Use Required() for fail-fast
gt.NoError(t, err).Required() // Stop immediately if error
gt.Value(t, result).NotNil().Required() // Stop if nil
Use Describef() for context
gt.Array(t, users).
Describef("Users for tenant %s", tenantID).
Length(5)
Handle function returns with R1/R2/R3
result := gt.R1(parseJSON(input)).NoError(t)
gt.String(t, result.Name).Equal("Alice")
Quick Reference
Constructors: gt.Value, gt.Array, gt.Map, gt.Number, gt.String, gt.Bool, gt.Error, gt.NoError, gt.File, gt.Cast, gt.R1/R2/R3
Short aliases: gt.V, gt.A, gt.M, gt.N, gt.S, gt.B, gt.F, gt.C
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.
- 6d ago First seen · 65 lines · 35 tokens per session scan A 89601d365fd0
test-with-gt is a skill published in the GitHub repository gollem-dev/gollem (193 stars, last pushed 6d ago), licensed Apache-2.0. It adds 35 tokens to every session and 634 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
increase-test-coverage
Increase Go test coverage to 90%+ using a Research → Plan → Implement pipeline. Analyzes coverage gaps, generates table-driven tests with httptest mocks, and validates results with go test -coverprofile. Designed for Go MCP server projects using the official go-sdk and gitlab.com/gitlab-org/api/client-go/v2.
go-testing
Use when writing, reviewing, or improving Go test code — including table-driven tests, subtests, parallel tests, test helpers, test doubles, and assertions with cmp.Diff. Also use when a user asks to write a test for a Go function, even if they don't mention specific patterns like table-driven tests or subtests. Does…
golang-testing
Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
golang-testing
Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.
go-expert
Expert-level Go development with Go 1.22+ features, concurrency, standard library, and production-grade best practices. Use when the user mentions concurrency, microservices, or backend, or when the task involves idiomatic Go, goroutines and channels, context-based cancellation, or writing an HTTP server.
go-safe-move-refactor
Safely move Go source files between packages with zero compilation downtime. Handles package declarations, import updates, symbol exports, type renames, test migration, and forwarding stubs. Validates compilation after every atomic step.