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 oggit 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/og)<a href="https://agentmods.dev/skills/ourobx/agent-ebpf/og"><img src="https://agentmods.dev/badge/skills/ourobx/agent-ebpf/og/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/og"><img src="https://agentmods.dev/badge/skills/ourobx/agent-ebpf/og.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 | $0.00223 | $0.01693 |
| Opus 5.5 | $0.00089 | $0.00677 |
| Sonnet 5.5 | $0.00045 | $0.00339 |
| Haiku 4.5 | $0.00022 | $0.00169 |
Grade A, and why
og 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Share cards, favicon, and app icons
A deployed app (https://{name}.grok.me) unfurls with a 1200×630 card; every app (preview included) shows a
favicon in the tab. Share-card <meta> tags are not authored in __root.tsx — the injector
(scripts/grok-pwa-shared.mjs) overwrites og:* and twitter:card on every HTML response. Identity data is
the only thing anyone writes, and the pass writes all of it — dispatching, you seed none of it:
src/lib/og/site.json— not pre-seeded, created only if needed:{ "title", "type"?: "x:game", "card"?: "custom", "color"?: "RRGGBB" }; title defaults to the host slug.public/og.jpg— custom 1200×630 card (optional; placeholder otherwise)public/x-banner.jpg— games only: 50:11 (1200×264) X feed cardpublic/favicon.svg— linked from roothead(); until the pass lands the tab just shows the browser default, which fails nothing
Extend __root.tsx; never replace it wholesale (auth SSR, redesigns, skill excerpts): dropping the
favicon link ships a blank tab icon no local check catches.
Decide: which card this app gets
Default: a custom card from the app's own art — games of every kind and rendering tech (Canvas/WebGL and DOM board, card, word, puzzle, quiz: a tic-tac-toe grid of divs is still a game), whimsical apps, creative tools, content- and brand-forward pages. When in doubt, make the custom card.
Plain utility apps only (converters, CRUD trackers, dashboards, notes/admin — apps whose face is the data)
keep the default og.grok.me placeholder: no public/og.jpg. Its URL, the "color" knob and the rename
rule: references/placeholder-card.md.
og:type for games
A game of any kind carries "type": "x:game" in src/lib/og/site.json — the pass writes it, owning that
file. No hostname, never gated on a custom card, never "corrected" to website, bare game, twitter:card
or an invented x:type: X's pipeline keys off that exact value. Non-games omit it. Your check, not your
edit — missing it, or missing public/x-banner.jpg once a custom card exists, is a BRAND WARNING.
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 · 103 lines · 223 tokens per session scan A 5c6ff71e4284
og is a skill published in the GitHub repository ourobx/agent-ebpf (1 stars, last pushed 1mo ago), licensed MIT. It adds 223 tokens to every session and 1,693 once invoked, about $0.0009 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
firewall
Production firewall management — UFW policy design, iptables/nftables rule authoring, stateful connection tracking, ingress/egress filtering, fail2ban integration, and firewall audit workflows for Linux servers.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).