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-reprogit 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-repro)<a href="https://agentmods.dev/skills/topman-14/mobius-mcp/mobius-repro"><img src="https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-repro/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-repro"><img src="https://agentmods.dev/badge/skills/topman-14/mobius-mcp/mobius-repro.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 | $0.00080 | $0.01022 |
| Opus 5 | $0.00040 | $0.00511 |
| Sonnet 5 | $0.00016 | $0.00204 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
mobius-repro 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 10d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mobius-repro
Not every bug gets fixed on the spot. Sometimes the right outcome is a well-documented issue, not a patch. Collecting a screenshot, the console output and the network detail by hand is exactly the copy-paste tedium this server exists to remove — this turns a live repro directly into something postable.
Drive the repro yourself where you can. A bug report whose steps you executed is one you know actually reproduces.
When to use this
- A bug is confirmed reproducible but the cause isn't clear, or fixing it is out of scope for this session.
- Handing a bug to someone else, or filing it for later.
- The user asks to "write this up," "document this," or "file an issue" for something just reproduced.
Workflow
mobius_diagnose. If it isn'tready, relay the remediation and stop.clear_logs, thenstart_debug_session(capture: ["console", "network", "navigation", "dom"])— the timeline is what makes the report reproducible by someone else.- Drive the repro with
run_sequence, recording the exact steps as you go: they become the numbered repro steps in the write-up. Usefindto locate controls andwait_for_*between steps rather than fixed delays. If a step genuinely can't be automated (a native file dialog, an external auth redirect, a payment step), ask the user to perform just that step and note it as manual in the report. - At the moment of failure,
take_screenshot— orcapture_full_pageif the relevant part is off-screen. Foreground the tab withswitch_tabfirst if needed. end_debug_sessionfor the ordered timeline.export_harfor a portable network record. This carries full request/response bodies, re-fetched over CDP where they weren't captured inline, so it stands alone as evidence.- Ask before writing anything to disk. Confirm whether they want a Markdown file (and where — default to something like
bug-reports/<short-slug>.mdunless they say otherwise) or whether a chat summary is enough. Some sessions just want it read back. - If they want a file:
- Decode the screenshot's
dataBase64to a real PNG next to the Markdown (<slug>-screenshot.png). Pipe the base64 throughbase64 -drather than pasting a data URI inline — a raw blob bloats the file and most renderers, GitHub included, won't inline it reliably. - Reference it normally:
. - Structure it as: title, environment (tab URL, browser, app version if visible), numbered repro steps someone else can follow, the screenshot, expected vs actual, the trimmed timeline, and the failing request(s) with status, headers and the relevant body fragment.
- Decode the screenshot's
- If just a summary is wanted, use the same structure as chat output with the screenshot described rather than embedded.
- If filing to GitHub is in scope, offer it once the write-up exists — don't create the file and open the issue without checking which the user wants.
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.
- 10d ago First seen · 47 lines · 80 tokens per session scan A 19b2f1aacc86
mobius-repro is a skill published in the GitHub repository Topman-14/mobius-mcp (18 stars, last pushed 21d ago), licensed MIT. It adds 80 tokens to every session and 1,022 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.
Other skills, from other repositories
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.