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 nWave-ai/nWave --skill nw-pbt-gogit clone --depth 1 https://github.com/nWave-ai/nWaveWrote 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/nwave-ai/nwave/nw-pbt-go)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-pbt-go"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-pbt-go/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/nwave-ai/nwave/nw-pbt-go"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-pbt-go.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 | $0.00015 | $0.01645 |
| Opus 5.5 | $0.00006 | $0.00658 |
| Sonnet 5.5 | $0.00003 | $0.00329 |
| Haiku 4.5 | $0.00002 | $0.00164 |
Grade A, and why
nw-pbt-go 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 4d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PBT Go -- rapid, gopter
Framework Selection
| Framework | Shrinking | Stateful | API Style | Choose When |
|---|---|---|---|---|
| rapid | Internal (Hypothesis-like) | Yes (StateMachine) | Idiomatic Go (*rapid.T) |
Default choice. Simpler API, better shrinking. |
| gopter | Type-based | Yes (commands) | Explicit generator construction | Need maximum control over generation |
Default: rapid. More idiomatic Go API and fully automatic shrinking.
Quick Start (rapid)
import (
"sort"
"testing"
"pgregory.net/rapid"
)
func TestSortPreservesLength(t *testing.T) {
rapid.Check(t, func(t *rapid.T) {
xs := rapid.SliceOf(rapid.Int()).Draw(t, "xs")
sorted := make([]int, len(xs))
copy(sorted, xs)
sort.Ints(sorted)
if len(sorted) != len(xs) {
t.Fatalf("length changed: %d -> %d", len(xs), len(sorted))
}
})
}
// Run: go test
Generator Cheat Sheet (rapid)
Primitives
rapid.Int() // any int
rapid.IntRange(0, 99) // bounded
rapid.Int32()
rapid.Float64()
rapid.String()
rapid.StringN(1, 50, -1) // min 1, max 50 chars
rapid.Bool()
rapid.Byte()
Collections
rapid.SliceOf(rapid.Int())
rapid.SliceOfN(rapid.Int(), 1, 10) // min 1, max 10 elements
rapid.MapOf(rapid.String(), rapid.Int())
Combinators
rapid.OneOf(rapid.Int(), rapid.Int32()) // does not work for different types
rapid.SampledFrom([]string{"a", "b", "c"})
rapid.Just(42)
// Map (transform)
rapid.Map(rapid.Int(), func(x int) int { return x * 2 }) // even integers
// Filter
rapid.Filter(rapid.Int(), func(x int) bool { return x > 0 })
// Prefer: rapid.IntRange(1, math.MaxInt)
// Custom generator (draw pattern)
func userGen(t *rapid.T) User {
return User{
Name: rapid.StringN(1, 20, -1).Draw(t, "name"),
Age: rapid.IntRange(1, 120).Draw(t, "age"),
}
}
// Use: rapid.Custom(userGen)
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.
- 4d ago First seen · 234 lines · 15 tokens per session scan A 8fad6010188d
nw-pbt-go is a skill published in the GitHub repository nWave-ai/nWave (631 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,645 once invoked, about $0.0001 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 2026-11-03.
nw-pbt-go compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nw-pbt-gonWave-ai/nWave | Skill | 631 | yesterday | MIT | A | 15 | Claude Code |
| mockery-suite-testsmakifbaysal/tasktrooper | Skill | 120 | 16d ago | Apache-2.0 | A | 63 | Claude Code, Codex |
| java-testing-junit-mockitomakifbaysal/tasktrooper | Skill | 120 | 16d ago | Apache-2.0 | A | 46 | Claude Code, Codex |
| golang-testing-patternscodeready-toolchain/tarsy | Skill | 10 | yesterday | Apache-2.0 | A | 47 | Cursor |
| golang-testingyzfly/skills | Skill | 12 | 1mo ago | none | A | 100 | Claude Code |
| golang-stretchr-testifyyzfly/skills | Skill | 12 | 1mo ago | none | A | 96 | Claude Code |
| rust-testingaffaan-m/ECC | Skill | 298k | 4d ago | MIT | A | 31 | Claude Code, Kiro |