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 Topman-14/mobius-mcp --skill mobius-broken-flowgit clone --depth 1 https://github.com/Topman-14/mobius-mcpWrote 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/topman-14/mobius-mcp/mobius-broken-flow)<a href="https://agentmods.dev/skills/topman-14/mobius-mcp/mobius-broken-flow"><img src="https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-broken-flow/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/topman-14/mobius-mcp/mobius-broken-flow"><img src="https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-broken-flow.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 | $0.00114 | $0.01441 |
| Opus 5 | $0.00057 | $0.00720 |
| Sonnet 5 | $0.00023 | $0.00288 |
| Haiku 4.5 | $0.00011 | $0.00144 |
Grade A, and why
mobius-broken-flow 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mobius-broken-flow
"It doesn't work" arrives with nothing to grep for — no stack trace, no message, just a control that seems inert or a flow that dies partway. That could be six different bugs, and reading source won't tell you which. Driving it while watching the runtime will, in one pass.
Don't ask the user to click anything. Drive it yourself and let the action report what it caused.
When to use this
- A button, link, or form that "does nothing," with no console error reported.
- A multi-step flow (signup, checkout, upload) that fails at a step nobody can pin down.
- A feature that used to work and now silently no-ops.
- Before digging through source — confirm what actually happens first.
Workflow
mobius_diagnose. If it isn'tready, relay the remediation and stop.clear_logs— without a clean baseline, "nothing happened" is ambiguous between truly nothing and buried in noise.find({ query: "..." })to locate the control by description ("submit order button"). ChecktotalMatched: exactly one is a confident hit, several means disambiguate byname/role/boxbefore acting. Fall back tosnapshot_page({ viewportOnly: true })to survey iffindcomes back empty.- Act with an observation window.
click(ref, { observe: { windowMs: 3000 } }). For a multi-step flow userun_sequence, giving the step you suspect its ownobserve. Address steps by CSSselectorrather thanrefif they follow a navigation — refs go stale, selectors resolve at step time. - Read
hitTestbefore anything else. If it's"blocked", that is the bug and the rest of the timeline is a red herring:covered—hitTestBlockedBynames the element eating the input. A modal backdrop, toast, or spinner left mounted; a full-screenopacity: 0layer withoutpointer-events: none.take_screenshotorcapture_elementto see it.pointer_events— the target haspointer-events: none, often paired with adisabledstate styled to look enabled.offscreen— the target's centre is outside the viewport.scroll_tofirst, then retry.
- Otherwise diagnose from
observed:- Empty — first confirm it's real: check
notCapturedin the response. If a category is off, you're blind, not looking at silence. If capture is on and it's genuinely empty, the handler never ran — see "Nothing fired" below. - Console, no network — client-side logic ran and stopped short. Validation blocked it, an exception was swallowed by an empty
catch, or state changed and nothing downstream reacted. - Request failed outright (
error, or 4xx/5xx) — a real error that never reached the UI. Find the missing.catch()or error boundary. - Request returned 200 but nothing changed — read
responseBodybefore touching frontend code. See "Successes that aren't" below.
- Empty — first confirm it's real: check
- Only now grep source, using what you learned to look for the specific gap.
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.
- 9d ago First seen · 57 lines · 114 tokens per session scan A 8cb79ea73732
mobius-broken-flow is a skill published in the GitHub repository Topman-14/mobius-mcp (18 stars, last pushed 20d ago), licensed MIT. It adds 114 tokens to every session and 1,441 once invoked, about $0.0006 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.