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 agentfront/frontmcp --skill frontmcp-auth-uigit clone --depth 1 https://github.com/agentfront/frontmcpWrote 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/agentfront/frontmcp/frontmcp-auth-ui)<a href="https://agentmods.dev/skills/agentfront/frontmcp/frontmcp-auth-ui"><img src="https://agentmods.dev/badge/skills/agentfront/frontmcp/frontmcp-auth-ui/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/agentfront/frontmcp/frontmcp-auth-ui"><img src="https://agentmods.dev/badge/skills/agentfront/frontmcp/frontmcp-auth-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 87 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 109 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 113 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 116 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 124 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Memory Poisoning · line 134 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 134 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 136 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 137 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00184 | $0.03049 |
| Opus 5.5 | $0.00074 | $0.01220 |
| Sonnet 5.5 | $0.00037 | $0.00610 |
| Haiku 4.5 | $0.00018 | $0.00305 |
Grade A, and why
frontmcp-auth-ui 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 8d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FrontMCP Custom Authorization UI (auth.ui)
Entry point for replacing FrontMCP's built-in OAuth pages (login, consent, federated, incremental, error) with your own React components. Custom UI is a simple slot→file map (auth.ui) plus an extras name→handler map (auth.extras) on the auth config — there is no decorator and no class. The references/custom-auth-ui.md reference has the full API; the examples/ show a single login slot and a multi-step extras form.
When to Use This Skill
Must Use
- Branding or fully replacing the
local/remotemode login page with a custom React component - Building a custom consent screen, federated provider picker, incremental authorization, or error page
- Adding a server-validated multi-step field to an authorization page (e.g. "add another item") via
auth.extras
Recommended
- Understanding which half is the server (
auth.ui/auth.extrasin@frontmcp/sdk) and which is the client (@frontmcp/ui/auth) - Looking up the
AuthFlowStatefields a slot component receives, or the/oauth/ui/extraroute - Confirming that the framework (not your component) owns CSRF + CSP
Skip When
- You only need to add/rename fields on the built-in login page or run a custom verifier — use the declarative
login/authenticateconfig infrontmcp-config→configure-authinstead (no React, no build step) - You are customizing a tool widget (not an auth page) — use
create-tool→ui-widgets - You don't need a custom page at all — configuring no
auth.uikeeps the built-in pages
Decision: Use this skill when you want to render your OWN component for an auth slot. Use
configure-auth's declarativeloginconfig when tweaking the built-in page's fields is enough.
Prerequisites
- A FrontMCP server in
localorremoteauth mode (seefrontmcp-config→configure-auth) @frontmcp/ui,react, andreact-dominstalled (react/react-domare peer deps of@frontmcp/ui)
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago Changed e6f5a3c3d1a9
- 1mo ago First seen · 147 lines · 184 tokens per session scan A 21e8cecb3a47
frontmcp-auth-ui is a skill published in the GitHub repository agentfront/frontmcp (146 stars, last pushed yesterday), licensed Apache-2.0. It adds 184 tokens to every session and 3,049 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
starchild-auth
Starchild Auth SDK: add OAuth login to any web app with one SDK. Use when integrating Starchild login into a project (e.g. add Starchild sign-in to my React app, set up OAuth with iamstarchild.com, implement login/logout with Starchild Auth SDK). Also use for local OAuth/CORS testing guidance (localhost:6066 web…
totp-oauth
Fermi's own OAuth 2.0 + TOTP owner authentication - how clients connect, how the 2FA login works, and how to roll it back.
nextjs-app-router-dev
A skill for developing and troubleshooting Next.js applications that use the App Router, including Edge middleware, SQLite, and session-based authentication.
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.
react-query-setup
Set up @trpc/tanstack-react-query with createTRPCContext(), TRPCProvider, useTRPC() hook, queryOptions/mutationOptions factories, query invalidation via queryClient.invalidateQueries with queryFilter, and type inference with inferInput/inferOutput.
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).