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-methodology/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-methodology)<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/research-methodology"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/research-methodology/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-methodology"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/research-methodology.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 | $0.05003 |
| Opus 5 | $0.00000 | $0.02501 |
| Sonnet 5 | $0.00000 | $0.01001 |
| Haiku 4.5 | $0.00000 | $0.00500 |
Grade B, and why
research-methodology scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls .claude/skills/ | grep -E '^(research-frontier|proof-and-analysis-toolkit|change-control|failure-archaeology)$' How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Methodology
This is not abstract scientific-method advice. Every rule below is reverse-engineered from a specific investigation in this repo's history, cited by issue/PR number. If you cannot point to the file, issue, or commit backing a claim, it does not belong in an issue, a PR description, or this skill.
Jargon: resilience review = a deliberate pass over recently-shipped code looking for latent
bugs before they reach users (not a response to an incident). Census = an empirical survey of
live/production data to check an assumption before coding against it. ADR = Architecture
Decision Record (docs/adr/).
1. The evidence bar
A proposed root cause is not accepted until it clears two hurdles:
1a. It must explain ALL observations, including the negatives
A mechanism that explains the symptom but not a related non-symptom is incomplete — ship the narrower fix and you will be back within the sprint.
Worked example — issue #308 (Future.wait([]) vacuous success):
- Symptom: a festival with
availableBeverageTypes: []locked the user to stale cache for up to an hour with no error signal. - First mechanism proposed:
isCompleteFailure(drinksByType.isEmpty && failedTypes.isNotEmpty) is false when both collections are empty, so the provider treats "no work to do" as "refreshed." The first commit fixed this by simply not updating_lastDrinksRefreshon the empty-success path. - The negative it didn't explain: switching from an already-loaded festival to an empty one.
_lastDrinksRefreshwas already set from the previous festival's real load, so leaving it untouched still leftisDrinksDataStalefalse — the switch-to-empty-festival case still locked up. - Full-explanation fix: a follow-up commit (
1fb41aa, PR #382) explicitly resets_lastDrinksRefresh = nullon the empty-success path, so a switch from a loaded festival to an empty one is correctly stale and retriable in both directions. - Lesson: when your fix only kills the reproduction case you tested, ask what the first commit's mechanism predicts for the adjacent case (here: switching state, not just cold state). If you can't answer that from the mechanism alone, you don't have the mechanism yet.
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 · 320 lines · 0 tokens per session scan B 55deab93e63c
research-methodology 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 5,003 tokens. A static security scan graded it B with 1 finding (enumerates other installed skills). 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…