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/madappgang/magus/testingnpx skills add MadAppGang/magus --skill testinggit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/testing)<a href="https://agentmods.dev/skills/madappgang/magus/testing"><img src="https://agentmods.dev/badge/skills/madappgang/magus/testing.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 | $0.00046 | $0.02691 |
| Opus 5 | $0.00023 | $0.01345 |
| Sonnet 5 | $0.00009 | $0.00538 |
| Haiku 4.5 | $0.00005 | $0.00269 |
Grade A, and why
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 3d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing in Bun
bun:test is jest-compatible and fast enough that the usual excuses for a thin suite do not
apply — a full server start, request and shutdown cycle runs in well under 50 ms (MEASURED,
asserted by a shipped test). The interesting decisions are therefore not "which runner" but
what to test, at what level, and how to keep it from lying to you.
Two things in this skill are measured behaviour you cannot guess:
coverageThresholdkeys are silently ignored when singular — your CI gate may be dead right now.spyOncalls through to the original by default — unlikejest.fn(), it is an observer, not a stub.
Both are below, with the measurements.
Test at the component level by default
The single highest-leverage choice. A component (API) test drives your real server over real HTTP:
✗ unit-mocking call handler(req) directly, mock the service, mock the repo
✓ component start the real server, POST /users, assert the response and the DB row
Calling a handler as a function skips routing, method matching, body parsing, header handling,
the error() hook and the status your framework actually produces. Every one of those has
shipped a bug. Worse, a suite built from mocks asserts that your mocks agree with each other —
it goes green while the real wiring is broken, which is the failure mode that erodes trust in a
suite until nobody reads it.
Reserve isolated unit tests for genuinely algorithmic code: pricing rules, parsers, state machines, backoff policy. Those have many input combinations and no I/O, which is exactly when isolation pays.
The five exit doors — what "assert enough" actually means
"Assert on outcomes, not interactions" is good advice that does not tell you when you are done. This does. A backend request can only affect the world through five doors, so for any feature, ask which it opens and assert on each:
| # | Exit door | Assert |
|---|---|---|
| 1 | Response | status, body, headers — the whole object, not one field |
| 2 | State change | the row that was written, deleted or left alone |
| 3 | External calls | the outgoing request you made, and its shape |
| 4 | Message queue | the message published, and its payload |
| 5 | Observability | the log line or metric an operator will page on |
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/testing/builders.test.ts 4.6 KB runs code
- assets/testing/builders.ts 4.4 KB runs code
- assets/testing/harness.test.ts 7.9 KB runs code
- assets/testing/harness.ts 9.0 KB runs code
- bun.lock 1.1 KB
- package.json 349 B
- references/bun-test-api.md 6.7 KB
- references/database-testing.md 8.9 KB
- references/external-services.md 5.1 KB
- references/test-strategy.md 7.1 KB
- tsconfig.json 324 B
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.
- 3d ago First seen · 208 lines · 46 tokens per session scan A ae2bea99af0a
testing is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 2,691 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 2026-08-31.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
pr-integration-test
Design, implement, and validate Intelligent Terminal integration tests for a target pull request or regression. Use when asked to add PR integration tests, convert a bug fix into E2E coverage, prove existing behavior still works, map tests to the release checklist, or verify E2E reports mark checklist cases complete.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.