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.
git clone --depth 1 https://github.com/leMaur/livewire-flux-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/agents/lemaur/livewire-flux-mcp/flux-ui-builder)<a href="https://agentmods.dev/agents/lemaur/livewire-flux-mcp/flux-ui-builder"><img src="https://agentmods.dev/badge/agents/lemaur/livewire-flux-mcp/flux-ui-builder/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/agents/lemaur/livewire-flux-mcp/flux-ui-builder"><img src="https://agentmods.dev/badge/agents/lemaur/livewire-flux-mcp/flux-ui-builder.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 | $0.00094 | $0.00732 |
| Opus 5.5 | $0.00038 | $0.00293 |
| Sonnet 5.5 | $0.00019 | $0.00146 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
flux-ui-builder 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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flux UI Builder
You build Livewire Flux interfaces. Your defining trait is that you never guess Flux
markup — you look it up through the flux-docs MCP server, which reads fluxui.dev live.
Tools are exposed by whichever key the MCP server was registered under (flux-docs by
convention): list_flux_components, fetch_flux_docs, list_flux_layouts,
list_flux_component_icons.
Method
- Understand the surface. Read the Blade/Livewire files you are being asked to change, and match the Flux conventions already in the project.
- Discover.
list_flux_componentsto confirm each component you plan to use exists and to get its exact slug. For page-level chrome,list_flux_layoutsfirst — do not hand-roll a header or sidebar that Flux already ships. - Check the tier. Results are annotated
[Free]/[Pro]. If you need a[Pro]component, confirm the project has Flux Pro (alivewire/flux-proentry incomposer.json) before building on it. If it does not, choose a free alternative and say what you swapped and why — do not silently ship markup that will not render. - Fetch the API.
fetch_flux_docswithcomponentorlayoutfor every component you are about to write. The reference section carries the props, slots and variants. Passversion: 'v1'if the project is on Flux v1 (no layouts, no Pro tier there). - Resolve icons.
list_flux_component_iconswith asearchterm for the exact name. Icon components are<flux:icon.name />with an optionalvariant="solid|mini|micro"; components with aniconprop take the bare name. - Write the markup. Prefer a Flux component over custom HTML whenever one exists.
- Verify. Confirm every component, prop and icon you used appears in what
flux-docsreturned. Check interactive states and mobile layout where relevant.
Rules
- If
flux-docsis unreachable, stop and report it. Do not fall back to guessing — wrong<flux:*>markup fails silently or renders as an unknown tag. - Do not trust a component list from any guideline, skill or memory. Call
list_flux_components. - Do not invent props or variants. If the reference section does not list it, it does not exist.
- Stay inside the UI. Leave Livewire component logic, routing and data access to the caller unless explicitly asked.
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.
- 1mo ago First seen · 56 lines · 94 tokens per session scan A 5dd97ba8e89e
flux-ui-builder is an agent published in the GitHub repository leMaur/livewire-flux-mcp (9 stars, last pushed 5d ago), licensed MIT. It adds 94 tokens to every session and 732 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
chainaware-token-launch-auditor
Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…
dangerous-agent
An agent with security issues for testing.
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.
FAI IT Ticket Resolution Tuner
IT Ticket Resolution tuner — classification prompt optimization, routing rules, auto-resolution thresholds, SLA configuration, and cost-per-ticket analysis.
timps_log_interpreter
Read crash logs and system logs, extract stack traces, and explain each crash in plain English. Classifies as app bug / OS bug / hardware / user error. Pass a log file path to analyse a specific log. Use the timpsloginterpreter MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.