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 joao-aires/agent-skills-public --skill journey-testinggit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/journey-testing)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/journey-testing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/journey-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/joao-aires/agent-skills-public/journey-testing"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/journey-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 | $0.00045 | $0.01443 |
| Opus 5.5 | $0.00018 | $0.00577 |
| Sonnet 5.5 | $0.00009 | $0.00289 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
journey-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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read workflow framing for skill selection and invocation boundaries.
Test what users depend on
Define the claim and boundary
Read the acceptance criteria and existing tests, then write down the user's goal and the observable result that completes it. Follow the journey through navigation, input, service work and the final state. Choose the important branches where a user could be blocked, receive misleading feedback or affect data they do not own.
Keep a small set of these journeys at the application level. Put detailed combinations of business rules and edge cases in focused unit or integration tests so browser/device checks remain understandable and practical to run. Preserve an existing suite and choose an actual platform driver compatible with the surface and claim below. Use installed tools for repeatable checks and exploratory operation; an MCP is optional. Keep regression tests and representative scenarios in the target application.
For a full-stack claim, exercise the real frontend, API and the application's actual persistence layer, with migrations applied where applicable. Preserve the selected database and exercise its actual transaction/persistence boundary. Keep external providers replaceable with controlled fixtures in routine CI; report that boundary. A mock API or browser-only demo proves a narrower claim and must be named as such.
Select the platform and evidence
| Surface | Evidence boundary |
|---|---|
| Web | Actual supported browsers, responsive sizes, keyboard/focus and relevant role variants |
| Desktop | Packaged application, native shell/IPC, lifecycle and OS integration on the supported target |
| Mobile | Each supported emulator/device platform, lifecycle, permissions, keyboard, offline and OS behavior |
Use available guidance for the selected development tools for chosen web/component drivers and native-platform implementation and driver expertise for supported native drivers. A mobile viewport cannot establish native behavior, a web preview cannot establish a packaged shell, and a backend run cannot establish client integration. Record actual device/OS/browser/build identities and missing capabilities; selecting a method does not install a driver or change the client framework.
What ships with it
2 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.
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.
- yesterday Changed · +27 lines 35490e3964c0
- 2d ago Changed · -2 lines 585864e9d68d
- 3d ago Changed · -2 lines 8537aa964f98
- 5d ago Changed · +7 lines 86cd4f908e91
- 7d ago First seen · 65 lines · 45 tokens per session scan A ba3a7b28797f
journey-testing is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,443 once invoked, about $0.0002 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 2026-10-15.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
create-verification-skill
Create a repo-local verification skill and exhaustive feature map for driving a real app through its UI, CLI, or API. Use for "create a verification skill", "make a verify skill for this repo", or "document how agents can verify this app".
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…