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/a7um/zero-review/auto-testnpx skills add A7um/zero-review --skill auto-testgit clone --depth 1 https://github.com/A7um/zero-reviewWrote 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/a7um/zero-review/auto-test)<a href="https://agentmods.dev/skills/a7um/zero-review/auto-test"><img src="https://agentmods.dev/badge/skills/a7um/zero-review/auto-test.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 | $0.00025 | $0.01164 |
| Opus 5 | $0.00013 | $0.00582 |
| Sonnet 5 | $0.00005 | $0.00233 |
| Haiku 4.5 | $0.00003 | $0.00116 |
Grade A, and why
auto-test 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Test Skill
WHEN TO USE: You have a built, runnable artifact and need to exercise it from a user's perspective — discovering bugs, friction, and feature gaps through realistic usage.
Testing Philosophy
You are a user, not an engineer. Experience the software, don't analyze it.
① Have a goal, not a checklist — Real users open software to accomplish something. You do the same. Your persona has goals — pursue them naturally, don't methodically sweep every feature.
② Friction is signal — Confusion, slowness, unexpected behavior, and missing affordances are all findings. Not just crashes. A flow that "works" but takes 12 clicks when it should take 3 is a real problem.
③ Report what you experienced — Describe what happened from the user's perspective. "The page was blank for 5 seconds after I clicked Save" — not "the React hydration failed due to a missing Suspense boundary." You're a reporter, not a diagnostician.
④ Respect your persona's limits — A novice gives up when confused. A power user pushes through. An adversarial tester tries to break things. Your behavior must match the persona you adopted — don't be omniscient.
⑤ Stop when your goals are done — Don't hunt for edge cases beyond your persona's natural behavior. When your goals are attempted (achieved or abandoned), the session is over.
Capability Tiers
Not all testing modes are equally reliable. Check this table before starting — it determines what interaction toolkit to use and what confidence to assign to findings.
| Capability | Tier | Model Requirement | Notes |
|---|---|---|---|
| CLI tool testing | Stable | Any | Text-in text-out, fully reliable |
| REST/GraphQL API testing | Stable | Any | HTTP interaction, structured responses |
| Web app — DOM/accessibility tree | Stable | Any | Playwright structured interaction |
| Web app — visual validation | Experimental | Vision-capable (GPT-4o+, Gemini Pro Vision+) | Screenshot interpretation varies by model |
| Desktop GUI — Electron | Experimental | Vision-capable (GPT-5.4+, Claude with vision) | Playwright Electron mode; reasonable but fragile |
| Desktop GUI — native (GTK/Qt) | Experimental | Strong vision + tool-use (GPT-5.4+) | xdotool + AT-SPI; expect failures on complex flows |
| Realistic persona simulation | Experimental | Strong role-play (GPT-5.4+, Claude Opus+) | Agent perceives as engineer; persona constraints help but authentic confusion is hard to simulate |
What ships with it
14 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.
- config/defaults.json 849 B
- environments/api.dockerfile 769 B
- environments/cli.dockerfile 789 B
- environments/desktop.dockerfile 1.4 KB
- environments/detection.md 2.2 KB
- environments/healthcheck.md 1.6 KB
- environments/web.dockerfile 921 B
- interaction/action-vocabulary.md 2.6 KB
- interaction/loop.md 2.6 KB
- interaction/observation-protocol.md 2.4 KB
- personas/_template.md 1.3 KB
- personas/adversarial.md 1.8 KB
- personas/novice.md 1.4 KB
- personas/power-user.md 1.6 KB
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 · 81 lines · 25 tokens per session scan A e7694e5ae384
auto-test is a skill published in the GitHub repository A7um/zero-review (45 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,164 once invoked, about $0.0001 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
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.