Borrowing it
Nothing to install: this file belongs to richardthe3rd/cambridge-beer-festival-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/richardthe3rd/cambridge-beer-festival-app/main/.claude/skills/research-frontier/SKILL.mdgit clone --depth 1 https://github.com/richardthe3rd/cambridge-beer-festival-appWrote 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/richardthe3rd/cambridge-beer-festival-app/research-frontier)<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/research-frontier"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/research-frontier/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/richardthe3rd/cambridge-beer-festival-app/research-frontier"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/research-frontier.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 | $0.00000 | $0.07473 |
| Opus 5 | $0.00000 | $0.03736 |
| Sonnet 5 | $0.00000 | $0.01495 |
| Haiku 4.5 | $0.00000 | $0.00747 |
Grade A, and why
research-frontier 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.
How it starts
The opening of the file, as written. The whole thing — 536 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Frontier
This skill is speculative by design. It is not a backlog, not a promise, and not architecture. Every claim below is labeled open (nobody has tried it) or candidate (a plausible first move, unproven). If you find yourself about to implement one of these as though it were decided, stop and read promotion path first — a frontier idea becomes real work only by passing through the same discipline as any other change.
When you should NOT be here: if the task is to ship a planned feature
(My Festival UI, cloud sync backend) use skill my-festival-campaign instead —
it is the executable, decision-gated version of problem 1 below. If the task
is "is this idea rigorous enough to act on", use skill research-methodology —
it supplies the evidence bar and idea lifecycle this skill's milestones must
satisfy.
What "state of the art" means for this project
The maintainer defined it directly, and it is the organizing idea for everything below:
Seamless offline/online — it just works in festival conditions (mobile-only data, patchy signal).
Festival attendees are in a marquee, on mobile data, competing with thousands of other phones on one cell tower. The real technical challenge is not "add more features" — it's "never let the network be visible to the user." Problem 1 is this headline problem stated directly. Problems 2–5 are narrower, supporting the same festival-conditions reality from other angles: identity across years, honest signal from strangers' phones, freshness without cost, and proving any of this actually works on Flutter web.
Problem 1 — Seamless offline/online personal-state sync under festival conditions
Status: open. This is the headline problem.
(a) Why naive approaches fail
The obvious approach — "send the write, retry on failure, show a spinner or a toast" — fails in festival conditions: a tasting note typed in a beer tent on one signal bar sees connect timeouts, DNS flaps, and mid-request drops, not clean up/down transitions. A naive retry-with-backoff loop either (1) blocks the UI waiting for a round-trip the user doesn't care about, or (2) silently drops the mutation when the app is backgrounded/killed before the retry fires. Neither answers the question that matters for trust: if I do this all day with the network flapping, do I end up with everything I entered, exactly once, on every device? That's a convergence property; "spinner" or "toast" UX is not a proof of it.
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 · 536 lines · 0 tokens per session scan A d5f60aeab896
research-frontier is a skill published in the GitHub repository richardthe3rd/cambridge-beer-festival-app (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,473 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…