Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/LandonSchropp/agent-toolkitnpx agentmods add skills/landonschropp/agent-toolkit/testing-bunWrote 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/landonschropp/agent-toolkit/testing-bun)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/testing-bun"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/testing-bun/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/landonschropp/agent-toolkit/testing-bun"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/testing-bun.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 | $0.00014 | $0.00589 |
| Opus 5.5 | $0.00006 | $0.00236 |
| Sonnet 5.5 | $0.00003 | $0.00118 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
testing-bun 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing with Bun
REQUIRED: fetch the Bun mocks documentation before writing or modifying tests.
Running the suite
Run the full suite via bun run test, never bun test directly. The script passes --isolate, which runs each test file in its own worker. Without it, mock.module() calls leak across files and tests fail in confusing, order-dependent ways.
For ad-hoc single-file runs, use bun test --isolate <file>.
Mock helpers
Prefer the specific mock helpers over mockImplementation:
mockResolvedValue(value)/mockResolvedValueOnce(value)— async functions returning a value.mockRejectedValue(error)/mockRejectedValueOnce(error)— async functions that throw.mockReturnValue(value)/mockReturnValueOnce(value)— sync functions.
Only reach for mockImplementation when behavior depends on arguments or call count.
Set mock return values close to the test that asserts on them, with the concrete value the test needs. Indirection through shared variables or transformations makes tests harder to read.
Spying on object methods
Never reassign properties on global or imported objects to stub them — use spyOn. Re-spy in beforeEach so each test starts from a known state.
// Good — spy, scoped to the test that needs it
import { spyOn } from "bun:test";
// Bad — reassigns the property
const original = Bun.stdin;
beforeEach(() => {
// @ts-expect-error
Bun.stdin = { json: () => Promise.resolve(payload) };
});
afterEach(() => {
// @ts-expect-error
Bun.stdin = original;
});
it("processes the payload", async () => {
spyOn(Bun.stdin, "json").mockResolvedValue({ hook_event_name: "Stop" });
// ... assertions
});
Mocking modules
Use static imports — Bun's ESM live bindings let mock.module() update modules that have already been imported. No dynamic await import() needed.
mock.module() returns a promise, so it must be awaited:
import { isGitInstalled } from "../../src/commands/git.ts";
import { describe, expect, it, mock } from "bun:test";
const runCommandMock = mock(() => Promise.resolve({ exitCode: 0, stdout: "", stderr: "" }));
await mock.module("../../src/commands/shell.ts", () => ({
runCommand: runCommandMock,
}));
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.
- 1mo ago Changed · +1 lines · +4 tokens per session 3d08bd1785bd
- 1mo ago First seen · 70 lines · 10 tokens per session scan A e6e4b1012397
testing-bun is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 589 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 2026-08-31.
Other skills, from other repositories
press-clip
Turn a live article URL into a press clip that looks like the real coverage — the publication's own logo, fonts, photos and layout kept intact, the ads and clutter removed, and (for a roundup) just the client's section. Renders to PDF. You inspect each site and tailor the removal; the bundled script carries no…
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
coverage-tracker
Run a Google Alerts-style keyword coverage tracker. Uses news-search for recent keyword queries, lets the LLM dedupe and classify real features versus junk, stores decisions in SQLite, and alerts only on new real coverage.
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…
coverage-tracker-setup
Set up a lightweight Google Alerts-style coverage tracker for any number of keywords. Creates a tracker config with each keyword and what it actually means, then hands recurrence to the user's agent harness.
prompt-set-qa
Gate a prompt universe for schema and provenance completeness, target or campaign contamination, evidence entailment, naturalness, one-concept clarity, architecture consistency, aided status, answer leakage, and semantic duplicates. Use after realistic prompt generation and before human panel selection.