cambridge-beer-festival-app: Skill for Claude Code

.claude/skills/my-festival-campaign/SKILL.md

my-festival-campaign is a skill for Claude Code from richardthe3rd/cambridge-beer-festival-app. It costs 227 tokens per session (8,573 once invoked), scanned A, original, MIT.

A step-by-step work plan for completing the “My Festival” feature in a beer-festival app, including its local diary screen and cloud backup. It covers both the Flutter app (a cross-platform mobile/web app toolkit) and the backend services.

In plain words
What is it for?
Use it to finish the tasting log, add local drink data handling, provision the D1 database, deploy the API, and connect the Flutter app to cloud sync.
Why use it?
It removes guesswork by defining the order of work, files to check, commands to run, and results required before moving on. It also keeps cloud backup separate from the app’s local source of truth.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; mentions AGENTS.md.

This is richardthe3rd/cambridge-beer-festival-app's own configuration. It tells Claude Code how to work on cambridge-beer-festival-app itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cambridge-beer-festival-app configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./bin/mise run check # generate → format → analyze → test → shell:check.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/richardthe3rd/cambridge-beer-festival-app/main/.claude/skills/my-festival-campaign/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/richardthe3rd/cambridge-beer-festival-app

Made for: Claude Code.

Wrote 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.

agentmods badge for my-festival-campaign

README.md
[![agentmods](https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/my-festival-campaign/github.svg)](https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/my-festival-campaign)
Your own site
<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/my-festival-campaign"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/my-festival-campaign/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.

agentmods 80×15 button for my-festival-campaign

Your own site · 80×15
<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/my-festival-campaign"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/my-festival-campaign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,573 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00227 $0.08573
Opus 5.5 $0.00091 $0.03429
Sonnet 5.5 $0.00045 $0.01715
Haiku 4.5 $0.00023 $0.00857

Measured 2mo ago against content hash 23c5a4334ef4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

my-festival-campaign scanned grade A 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS https://data.cambeerfestival.app/health
.claude/skills/my-festival-campaign/SKILL.md · 617 lines

How it starts

The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.

My Festival campaign — Phase 1 UI + cloud sync

This is a runbook, not a design doc. Each phase names exact files, gives a baseline command and a verification command, states the observation you should see at the gate, and tells you where to branch if you see something else. Do the phases in order within a track; one PR per phase.

Read as ground truth before starting: docs/planning/my-festival/vision.md (the product spec) and the proto contract in proto/cambeerfestival/festival/v1alpha/ (drink_entry.proto, my_festival_service.proto). Verify any file:line claim below against the code before you rely on it — the tree moves.

Two independent tracks

  • Track A — UI (#411 → #413 → #414 → #415): local diary. All data stays in SharedPreferences. This is the maintainer's stated hardest live problem and the higher-value track — do it first.
  • Track B — Sync (D1 + worker + Flutter client): additive backup. Can start after A1 lands (A1 finalises the local UserDrinkState shape that sync serialises). Per vision.md Phase 3, sync is strictly additive — SharedPreferences stays the source of truth for the UI; the network is a backup, never a read dependency.

Interleaving is fine, but never let Track B change UI behaviour. If a sync PR touches a screen, you have crossed the tracks — split it.

Doc-drift warnings (trust code, not these docs)

  • docs/planning/rating-service/design.md is stale. It describes Firebase Anonymous Auth and a RatingsService in storage_service.dart. Neither is real. The deployed worker uses an X-Device-Id header for identity (no Firebase auth), and RatingsService/FavoritesService/TastingLogService were unified into UserDataStore (lib/services/user_data_store.dart) by #391/#395. storage_service.dart now holds only FestivalStorageService. Use the design doc for intent only; use the proto + cloudflare-worker/ + the code for contract.
  • AGENTS.md still lists those three deleted services in its Architecture section — same drift, same resolution.
  • Deployed API ≠ full proto contract. The proto describes a DrinkEntry resource (.../entry, drinkEntries) carrying is_favourite, star_rating, would_recommend, note, pours. The worker only implements the narrower Review (.../review, reviews, reviewSummaries) carrying starRating
    • wouldRecommend. The DrinkEntry sync endpoint is not built — see B3.

Read the full file on GitHub · 617 lines

Changes

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.

  1. 2mo ago Changed · +6 lines 23c5a4334ef4
  2. 2mo ago First seen · 611 lines · 227 tokens per session scan A f9de11113504

Subscribe to this mod's changes

my-festival-campaign is a skill published in the GitHub repository richardthe3rd/cambridge-beer-festival-app (3 stars, last pushed today), licensed MIT. It adds 227 tokens to every session and 8,573 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

my-festival-campaign compared with skills from other repositories

my-festival-campaign next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
my-festival-campaignrichardthe3rd/cambridge-beer-festival-appSkill3todayMITA227Claude Code
orca-emulator-androidstablyai/orcaSkill117kyesterdayMITA102Claude Code, Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
android-tombstone-symbolicationdotnet/skillsSkill5.8kyesterdayMITA176Claude Code
dogfoodcallstack/agent-deviceSkill5.3kyesterdayMITA55Claude Code
winapp-mauimicrosoft/winappCliSkill1.4kyesterdayMITA68Claude Code
app_remixrome-os/romeSkill889yesterdayMITA50Claude Code, Codex