agentmods.dev

mobius-walkthrough

mobius-walkthrough is a skill for Claude Code from Topman-14/mobius-mcp. It costs 83 tokens per session (849 once invoked), scanned A, original, MIT.

A guided check of important user journeys in a real, logged-in application session. It records a verdict, screenshot, network activity, and browser-console output for each step.

In plain words
What is it for?
Use it to smoke-test staging, check an application before or after deployment, verify that a change did not break related journeys, and repeat a flow after a fix.
Why use it?
It helps find release regressions and deployment problems when there is no automated test suite, or when automated tests pass but users still report failures. It provides evidence for each flow instead of only a pass or fail count.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mobius-mcp plugin — 5 skills shipped together

not rated 18repo 20d ago A scan 83 tokens original MIT

Good fit Use it to smoke-test staging, check an application before or after deployment, verify that a change did not break related journeys, and repeat a flow after a fix.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/topman-14/mobius-mcp/mobius-walkthrough
View source ↗ Topman-14/mobius-mcp
Install

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.

Any agent
npx skills add Topman-14/mobius-mcp --skill mobius-walkthrough
Clone the repo
git clone --depth 1 https://github.com/Topman-14/mobius-mcp

Made for: Claude Code.

Or install mobius-mcp, the plugin that ships this one along with the rest of its 5 skills.

Wrote 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.

agentmods badge for mobius-walkthrough

README.md
[![agentmods](https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-walkthrough/github.svg)](https://agentmods.dev/skills/topman-14/mobius-mcp/mobius-walkthrough)
Your own site
<a href="https://agentmods.dev/skills/topman-14/mobius-mcp/mobius-walkthrough"><img src="https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-walkthrough/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.

agentmods 80×15 button for mobius-walkthrough

Your own site · 80×15
<a href="https://agentmods.dev/skills/topman-14/mobius-mcp/mobius-walkthrough"><img src="https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-walkthrough.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 849 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.00849
Opus 5 $0.00042 $0.00425
Sonnet 5 $0.00017 $0.00170
Haiku 4.5 $0.00008 $0.00085

Measured 9d ago against content hash 55ebf47179d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mobius-walkthrough 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 9d 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.

skills/mobius-walkthrough/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mobius-walkthrough

A regression sweep an agent can run against a real, logged-in session — no fixtures, no test account, no selectors written in advance. The output is a per-flow verdict backed by evidence, not a pass/fail count.

This is not a replacement for a test suite. It's what you run when there isn't one, or when the suite passes and users still report breakage.

When to use this

  • "Check that the app still works" before or after a deploy.
  • Verifying a change didn't break neighbouring flows.
  • Smoke-testing a staging environment that has no automated coverage.
  • Re-running a flow after a fix, to compare against how it failed before.

Workflow

  1. mobius_diagnose. If it isn't ready, relay the remediation and stop.
  2. Agree the flows first. If the user hasn't named them, propose a short list from the app's structure (routes, nav, README) and confirm before driving — a walkthrough that exercises the wrong things wastes the session. Keep it to the handful that matter.
  3. Decide what's safe to touch. Ask before anything destructive or outward-facing: submitting real orders, sending messages or invites, deleting records, changing account settings, anything that spends money. On a production or shared environment, prefer read-only paths and stop to check rather than guessing.
  4. For each flow, drive it as one run_sequence:
    • find the entry point, then chain the steps. Address by CSS selector rather than ref for anything after a navigation.
    • Put observe: { windowMs } on steps that submit, save, or load data — that's where failures hide.
    • Interleave take_screenshot at the points a human would want to see: after landing, after a submit, at the end state.
    • Use wait_for_navigation / wait_for_element between steps rather than fixed delays.
  5. Read each flow's transcript for: any hitTest: "blocked", any 4xx/5xx, any 200 with an error-shaped responseBody, any console error, and whether the expected end state was actually reached. A flow that "completed" without reaching its end state is a failure, not a pass.
  6. clear_logs between flows so each one's evidence stands alone.
  7. Report per flow: worked / broke / couldn't complete, and for anything not working, the specific evidence — the failing request and its body, the blocked click and what blocked it, the console error. Attach the screenshots. Do not report a bare count.

Read the full file on GitHub · 41 lines

Changes

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.

  1. 9d ago First seen · 41 lines · 83 tokens per session scan A 55ebf47179d3

Subscribe to this mod's changes

mobius-walkthrough is a skill published in the GitHub repository Topman-14/mobius-mcp (18 stars, last pushed 20d ago), licensed MIT. It adds 83 tokens to every session and 849 once invoked, about $0.0004 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.

Browser automationE2E testingTesting
Related

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).

garrytan/gstack · 32 tokens

playwright-cli

A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.

UnicomAI/wanwu · 76 tokens

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.

anthropics/skills · 35 tokens

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".

get-bb/bb · 57 tokens

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.

hashgraph-online/awesome-codex-plugins · 58 tokens

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…

PostHog/posthog-foss · 112 tokens