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 5.5 | $0.00094 | $0.02613 |
| Sonnet 5.5 | $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 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 -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.
- 2mo 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 (3 stars, last pushed today), licensed MIT. It adds 235 tokens to every session and 6,533 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.
run-and-operate compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| run-and-operaterichardthe3rd/cambridge-beer-festival-app | Skill | 3 | today | MIT | A | 235 | Claude Code |
| orca-emulator-androidstablyai/orca | Skill | 117k | yesterday | MIT | A | 102 | Claude Code, Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| android-tombstone-symbolicationdotnet/skills | Skill | 5.8k | yesterday | MIT | A | 176 | Claude Code |
| dogfoodcallstack/agent-device | Skill | 5.3k | yesterday | MIT | A | 55 | Claude Code |
| winapp-mauimicrosoft/winappCli | Skill | 1.4k | yesterday | MIT | A | 68 | Claude Code |
| app_remixrome-os/rome | Skill | 889 | yesterday | MIT | A | 50 | Claude Code, Codex |