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/run-and-operate/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/run-and-operate)<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/run-and-operate"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/run-and-operate/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/run-and-operate"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/run-and-operate.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 | $0.00235 | $0.06533 |
| Opus 5 | $0.00118 | $0.03266 |
| Sonnet 5 | $0.00047 | $0.01307 |
| Haiku 4.5 | $0.00023 | $0.00653 |
Grade A, and why
run-and-operate 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://data.cambeerfestival.app/health How it starts
The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run and Operate
This skill covers doing things: running the app, building artifacts,
deploying them, and knowing where the results land. It assumes the toolchain
is already installed (see skill build-and-env if ./bin/mise itself is
broken) and that you've already cleared change control for whatever you're
about to ship (see skill change-control for gates/policy — this skill does
not repeat them).
All commands below were verified against mise.toml, mise.dev.toml,
mise-tasks/**, and .github/workflows/** on 2026-07-02. Re-run the checks
in "Provenance and maintenance" before trusting a command that looks stale.
1. Run matrix
| Goal | Command | Notes |
|---|---|---|
| Dev server | MISE_ENV=dev ./bin/mise run dev |
flutter run -d web-server --web-port 8080 --pid-file flutter-dev.pid (mise-tasks/dev.sh). Serves http://localhost:8080. On Claude Code Web, omit MISE_ENV=dev — .miserc.toml already selects claude-code-web,dev when CLAUDE_CODE_REMOTE=true; an explicit MISE_ENV overrides that file and drops the web env. |
| Local web build (for e2e) | MISE_ENV=dev ./bin/mise run build:web |
flutter build web --release --base-href "/" (mise-tasks/build/web.sh). No dart-defines. Output: build/web/. |
| Production-shaped web build | MISE_ENV=dev ./bin/mise run build:web:prod |
Runs scripts/get_version_info.sh export first, then flutter build web --release --base-href "/" with --dart-define=GIT_TAG=..., GIT_COMMIT, GIT_BRANCH, BUILD_VERSION, BUILD_TIME (mise-tasks/build/web/prod.sh). Does NOT pass --source-maps — for a crash-decodable local build and the full decode workflow see skill diagnostics-and-tooling §2. |
| Serve a release build locally | MISE_ENV=dev ./bin/mise run serve:release |
npx http-server build/web -p 8080 --proxy http://localhost:8080? (mise-tasks/serve/release.sh). The --proxy flag is the SPA-fallback trick: any path http-server can't find as a static file gets re-requested through the proxy, which serves index.html — this is what makes deep links like /cbf2026/drink/beer/123 work when refreshed against a static file server. Errors loudly if build/web doesn't exist yet — build first. |
| Android debug/release build (local) | flutter build apk --release / flutter build appbundle --release |
No mise task wraps this (confirmed: ./bin/mise tasks ls has no build:android* entry) — these are the one place AGENTS.md's "never run raw flutter" rule doesn't apply, because there is nothing to wrap. Debug-signed locally (no android/key.properties) unless you've set one up per docs/tooling/android-release.md. Outputs: build/app/outputs/flutter-apk/app-release.apk, build/app/outputs/bundle/release/app-release.aab. |
| e2e recipe (local, once per machine) | see below |
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 · 438 lines · 235 tokens per session scan A f9f8ac68f857
run-and-operate is a skill published in the GitHub repository richardthe3rd/cambridge-beer-festival-app (2 stars, last pushed yesterday), licensed MIT. It adds 235 tokens to every session and 6,533 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
react-native-ease-refactor
Scan for Animated/Reanimated code and migrate to EaseView.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…