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 justhamade/triadjs --skill triad-testinggit clone --depth 1 https://github.com/justhamade/triadjsWrote 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/justhamade/triadjs/triad-testing)<a href="https://agentmods.dev/skills/justhamade/triadjs/triad-testing"><img src="https://agentmods.dev/badge/skills/justhamade/triadjs/triad-testing/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/justhamade/triadjs/triad-testing"><img src="https://agentmods.dev/badge/skills/justhamade/triadjs/triad-testing.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 | $0.00068 | $0.01536 |
| Opus 5.5 | $0.00027 | $0.00614 |
| Sonnet 5.5 | $0.00014 | $0.00307 |
| Haiku 4.5 | $0.00007 | $0.00154 |
Grade A, and why
triad-testing 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing with TriadJS
TriadJS tests run in-process. The runner invokes endpoint.handler(ctx) directly with a synthetic HandlerContext. No HTTP, no adapter, no JSON serialization. This makes tests fast and deterministic, and it means behaviors must not depend on Fastify/Express middleware.
triad.config.ts
Project root config file. Loaded with jiti, so TypeScript works with no build step.
import { defineConfig } from '@triadjs/test-runner';
export default defineConfig({
router: './src/app.ts', // module default-exporting the Router
test: {
setup: './src/test-setup.ts', // default-exports a services factory
teardown: 'cleanup', // method name on the returned services object
bail: false,
},
docs: {
output: './generated/openapi.yaml',
format: 'yaml', // or 'json'
},
gherkin: {
output: './generated/features',
},
});
| Field | Purpose |
|---|---|
router |
Path to the Router module (default export), resolved relative to the config file |
test.setup |
Path to a module whose default export is a services factory |
test.teardown |
Name of a method to call on the services object after each scenario |
test.bail |
Stop on first failure |
docs.output / docs.format |
Where triad docs writes |
gherkin.output |
Where triad gherkin writes |
Configs are discovered by walking upward from the cwd unless --config is passed.
test-setup.ts — per-scenario isolation
Every scenario gets a fresh services container. The test setup file default-exports a factory:
// src/test-setup.ts
import { createServices } from './services.js';
import { createDatabase } from './db/client.js';
interface TestServices extends ReturnType<typeof createServices> {
cleanup(): Promise<void>;
}
export default function createTestServices(): TestServices {
const db = createDatabase(':memory:'); // fresh in-memory DB per scenario
const services = createServices({ db });
return {
...services,
async cleanup() {
services.db.$raw.close();
},
};
}
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 · 141 lines · 68 tokens per session scan A 14e7b4b8f9a2
triad-testing is a skill published in the GitHub repository justhamade/triadjs (24 stars, last pushed 6mo ago), licensed MIT. It adds 68 tokens to every session and 1,536 once invoked, about $0.0003 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 2026-08-30.
triad-testing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| triad-testingjusthamade/triadjs | Skill | 24 | 6mo ago | MIT | A | 68 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |