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 abel30567/fermi-mcp --skill totp-oauthgit clone --depth 1 https://github.com/abel30567/fermi-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/abel30567/fermi-mcp/totp-oauth)<a href="https://agentmods.dev/skills/abel30567/fermi-mcp/totp-oauth"><img src="https://agentmods.dev/badge/skills/abel30567/fermi-mcp/totp-oauth/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/abel30567/fermi-mcp/totp-oauth"><img src="https://agentmods.dev/badge/skills/abel30567/fermi-mcp/totp-oauth.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 | $0.00038 | $0.00468 |
| Opus 5 | $0.00019 | $0.00234 |
| Sonnet 5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
totp-oauth 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 12d 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.
What it actually says
Fermi OAuth 2.0 + TOTP owner auth
Built in PR #5 (issue #4); provider refactored onto
@cloudflare/workers-oauth-provider (issue #7). Protects the MCP endpoints and
private R2-hosted apps.
Flow
- MCP client hits
/mcpor/sse; with auth enabled it is redirected into the OAuth flow at/oauth/authorize(PKCE required, plain PKCE disallowed). - The authorize page asks for the owner secret + a 6-digit TOTP code
(Google Authenticator, seeded from
{{secret:FERMI_TOTP_SECRET}}). - On success the provider issues tokens via
/oauth/token; client registration is at/oauth/register(scope:mcp). - Private apps under
/apps/*use the same owner+TOTP login at/apps/_login; the session cookie lasts 24h./apps/public/*skips auth entirely.
Rollback flag
FERMI_AUTH_ENABLED (worker var). 'true' routes everything through the
OAuthProvider; any other value serves the default handler with no auth. If auth
breaks (e.g. client Zod validation of redirect_uris), set it to 'false',
redeploy, and debug offline.
Gotchas
- TOTP codes are all-numeric — a historical regex bug rejected valid codes (fixed in #9); validate with a numeric-aware pattern.
- The owner secret and TOTP seed live in the secrets store; never hardcode them.
- Token lifetimes follow the provider defaults; the apps session cookie (24h) is independent of MCP tokens.
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.
- 12d ago First seen · 35 lines · 38 tokens per session scan A 81daccd09f1b
totp-oauth is a skill published in the GitHub repository abel30567/fermi-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 468 once invoked, about $0.0002 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 2026-08-31.
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…
frontmcp-auth-ui
Use when customizing, branding, or replacing the built-in FrontMCP OAuth pages (the login, consent, federated-select, incremental-authorization, and error pages) with your own React components. Covers the auth.ui slot-to-file map and auth.extras name-to-handler map on the auth config (no decorator, no class); the…
google-cloud-auth
Skill "google-cloud-auth" from VKirill/claude-lane-stack, covering 🎯 version requirements (june 2026), usage, use this skill when, do not use this skill when and purpose.
hunt-auth-bypass
Hunting skill for auth bypass vulnerabilities. Built from 12 public bug bounty reports across SAML XSW / parser-differential (GitHub Enterprise CVE-2025-25291/25292), SAML signature stripping (Uber, Rocket.Chat, samlify CVE-2025-47949), SAML domain enforcement bypass via control characters (HackerOne 2024)…
frontmcp-config
Use when configuring a FrontMCP server through frontmcp.config or the @FrontMcp options. Covers auth modes (public, transparent, local, remote), OAuth plus credential vault and secureStore, CORS, HTTP port / entry-path prefix / unix socket, security headers (CSP, HSTS, X-Frame-Options, X-Content-Type-Options), rate…
api-connector-builder
Use when writing a client for someone else's REST or GraphQL API: auth flow choice and token refresh, pagination to exhaustion, retry-with-jitter on transient failures only, rate-limit-aware throttling. NOT inbound callbacks (that is webhooks), NOT chaining services (that is automation-flows), NOT designing your own…