mobius-mcp
01Plugin Claude Code
Plugin marketplace listing 1 plugin: mobius-mcp.
18 12d ago A
tokens not measured
original MIT
mobius-mcp
02Plugin Claude Code
Scenario-focused skills for driving and debugging a running web app via the mobius-mcp MCP server — broken flows, QA walkthroughs, bug repros, perf stakeouts, and page audits.
18 12d ago A
tokens not measured
original MIT
Instructions file
Instructions for Topman-14/mobius-mcp, covering claude.md, commands, setup, build and watch mode (active development).
18 12d ago A 3,055 tokens
original MIT
Skill Claude CodeCodex
Diagnose a UI interaction or multi-step flow that doesn't work — a button that appears to do nothing, a form that won't submit, a step that silently fails — by driving it and reading what the app actually did. Separates a handler that never fired, a click eaten by an overlay, a request that failed, a 200 carrying an…
18 12d ago A 114 tokens
original MIT
Skill Claude CodeCodex
Audit what a page actually does at runtime — every third-party request and what's in its payload, whether anything sensitive leaves in a request body, console noise and errors, and controls that render but can't be reached or activated. Use to review a page before shipping, check what an embedded script is sending, or…
18 12d ago A 82 tokens
original MIT
Skill Claude CodeCodex
Diagnose "this feels slow" by isolating whether an interaction is network-bound, JS/CPU-bound, a memory leak, or a render loop/race condition from bad JS (React useEffect, framework reactivity bugs). Use for sluggishness or jank reports with no obvious cause, via mobius-mcp.
18 12d ago A 73 tokens
original MIT
mobius-repro
07Skill Claude CodeCodex
Turn a reproduced bug into a filable artifact — screenshots, an ordered console/network/navigation timeline, and a HAR with full request/response bodies — suitable for a GitHub issue or a handoff. Offers to save it as Markdown with the screenshot embedded. Use once a bug is confirmed but needs escalating, filing, or…
18 12d ago A 80 tokens
original MIT
Skill Claude CodeCodex
Drive a set of key user flows end to end and report what broke, collecting a screenshot, network activity and console output per step. A regression sweep before a release, or a smoke test of a deploy, without a test suite to maintain. Use when asked to check whether an app still works, verify a release, or exercise…
18 12d ago A 83 tokens
original MIT