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 ourobx/agent-ebpf --skill authgit clone --depth 1 https://github.com/ourobx/agent-ebpfWrote 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/ourobx/agent-ebpf/auth)<a href="https://agentmods.dev/skills/ourobx/agent-ebpf/auth"><img src="https://agentmods.dev/badge/skills/ourobx/agent-ebpf/auth/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/ourobx/agent-ebpf/auth"><img src="https://agentmods.dev/badge/skills/ourobx/agent-ebpf/auth.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 | $0.00083 | $0.01653 |
| Opus 5.5 | $0.00033 | $0.00661 |
| Sonnet 5.5 | $0.00017 | $0.00331 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
auth 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auth
This app runs its own Better Auth at
/api/auth/*, federating to the shared Grok auth broker (auth.grok.me)
via the genericOAuth plugin. This template wires Google and X.
Supported sign-in methods — use ONLY these three; nothing else is supported:
Google, X, and email/password. No other social/OAuth provider (GitHub, Apple,
Discord, …), no magic links, passkeys, OTP, phone/SMS, or anonymous sign-in. Do
not add entries to GROK_PROVIDERS. Method detail and the email/password switch
(edit only src/lib/auth/email-password.ts): references/sign-in-methods.md.
Exception — connector / app-data apps sign in ONLY via "Continue with Grok"
gate sign-in, no Google/X buttons: references/grok-identity.md.
Sign-in is OFF by default — the template ships .grok/app-env.json with
{"VITE_AUTH_ENABLED": "false"}, so only add accounts when the ask calls for
them (AGENTS.md §0.5). Switching it on is "Turning sign-in on" below.
Once on, sign-in is REAL — including in the sandbox live preview. Build real
sign-in; do NOT scaffold demo/mock/hardcoded users. Preview: popup + baked
preview client; deployed: per-app client + DATABASE_URL + zero-click gate
sign-in (references/prewired-and-env.md, references/grok-identity.md).
While OFF (VITE_AUTH_ENABLED=false) a dev user is returned so a
non-auth app renders without a signed-in visitor — dev and preview only. The
deployed flag is the deployer's (always "true" today), so deployed,
requireUserId rejects every visitor; an app without sign-in uses neither
authMiddleware nor requireUserId.
Everything is preinstalled and pre-wired in src/lib/auth/ — do not
npm install anything; better-auth is the only auth package (never
@neondatabase/*, @stackframe/*, or @clerk/*). Do not edit or rewrite any
file under src/lib/auth/ — server.ts least of all — except
email-password.ts for its one flag. Per-file map:
references/prewired-and-env.md.
/auth/popup is already handled by the template Vite plugin
(vite.config.ts → popup.server.ts): it never paints the React app. Do NOT
create src/routes/auth/popup.tsx (or any React page / client OAuth at that
path) — that shows the full app inside the popup, the common failure mode.
Never write a .env / .env.local / .env.example in this sandbox: live
preview needs zero env configuration and a deployed app gets its vars
injected by the platform. The knobs that exist are in
references/prewired-and-env.md — never expose a non-VITE_ var to the client.
migrations/auth/0001_auth.sql is the Better Auth schema — do not edit. It
sits outside the globbed migrations/ directory (neither applier descends), so
it is not applied to apps without sign-in; "Turning sign-in on" copies it up.
What ships with it
6 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.
- 1mo ago First seen · 111 lines · 83 tokens per session scan A dd944f1cf735
auth is a skill published in the GitHub repository ourobx/agent-ebpf (1 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,653 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
unifi-connect
Use when connecting an agent to a UniFi gateway (UDM Pro, UDM SE, Cloud Gateway) for the first time, or when API calls to one are failing: empty response bodies, curl returning HTTP 000, 401 on a key that works elsewhere, "how do I get a UniFi API key", "SSH is closed on my UDM", "connect to UniFi", "talk to my UniFi…
srx-mpls-in-flow
Design, configure, audit, and troubleshoot Juniper SRX MPLS L3VPN in flow mode. Use when handling Junos 24.2R1+ family mpls with inet or inet6 flow, secure PE or CPE, VRFs, LDP, MP-BGP, l3vpn vrf-group policy, VRF-to-zone mapping, VRF-aware NAT or AppID, PowerMode or RFP, MTU, labels, or policy matching.
waf-bypass-hunter
Bypass a Coraza WAF protecting a vulnerable Next.js 16 backend. Analyze parser differentials between Go (WAF) and Node.js (backend) to find bypasses.
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".