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/AGENTS.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/instructions/richardthe3rd/cambridge-beer-festival-app/agents-md)<a href="https://agentmods.dev/instructions/richardthe3rd/cambridge-beer-festival-app/agents-md"><img src="https://agentmods.dev/badge/instructions/richardthe3rd/cambridge-beer-festival-app/agents-md/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/instructions/richardthe3rd/cambridge-beer-festival-app/agents-md"><img src="https://agentmods.dev/badge/instructions/richardthe3rd/cambridge-beer-festival-app/agents-md.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 | $0.08182 | $0.08182 |
| Opus 5.5 | $0.03273 | $0.03273 |
| Sonnet 5.5 | $0.01636 | $0.01636 |
| Haiku 4.5 | $0.00818 | $0.00818 |
Grade A, and why
cambridge-beer-festival-app AGENTS.md 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 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.
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 — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Instructions
Instructions for AI coding agents (Claude, Copilot, etc.) working on the Cambridge Beer Festival app.
Session Startup
At the start of every session, kick off toolchain installation in the background before doing anything else. Flutter, Dart, and pub dependencies are managed by mise and may not be present in a fresh environment. Installation can take 2–5 minutes; starting it immediately means it's ready by the time you need it.
# Run this first — before reading code, planning, or asking questions
./bin/mise run check &
check runs generate → analyze → test, which forces mise to install Flutter and fetch pub dependencies as a side effect. Running it in the background lets you proceed with reading files, understanding the task, and drafting a plan while tools install. When you're ready to run a command that needs Flutter, wait for the background job to finish or check its status.
If check fails due to missing system deps (e.g. no network, missing system libraries), fall back to just fetching deps:
./bin/mise deps &
Do not run raw flutter commands — they may use the wrong version. Always use ./bin/mise run <task>.
Skill Routing
This file is the always-on spine: universal rules and safety tripwires. The depth lives in skills (loaded on demand). When your task matches a row, load that skill — it has the file:line detail, the incident history, and the exact commands.
| When you're… | Load skill |
|---|---|
| understanding how the app is built; deciding where state/logic lives; adding a screen, model, service, sort option, or persisted field | architecture-contract |
| writing or judging any test; updating goldens; TDD; semantics tests; "is this tested enough" | validation-and-qa |
touching lib/screens/**, lib/widgets/**, main.dart, app_theme.dart — any visual change, restyle, new widget, or Semantics |
ui-and-accessibility |
aesthetic/visual-identity direction for a new UI or a from-scratch redesign — palette, typography pairing, layout concept, avoiding templated defaults (load alongside ui-and-accessibility, which governs this repo's Flutter/a11y rules) |
frontend-design |
| committing, opening/merging a PR, deciding if a change is allowed, which CI gate fires, review-comment triage | change-control |
running/building/serving/deploying, provisioning D1, cutting a release, editing festivals.json |
run-and-operate |
| setting up the toolchain; mise/install failures; env vars; CI-vs-local parity; adding a mise task | build-and-env |
| measuring/decoding — test/analyze logs, minified web-crash stacks, coverage, headless page checks | diagnostics-and-tooling |
| figuring out what a symptom MEANS — stale drinks, festival flash, web crash, flaky test, CI/worker error | debugging-playbook |
editing proto/** or cloudflare-worker/reviews.ts / shared.ts; any AIP / API-contract review comment |
api-contract |
| the history behind a decision — "didn't we try this", "why was X removed", rejected alternatives, ADRs | failure-archaeology |
what a domain term MEANS — dispense, allergens, status_text, D1, etag, AIP, CalVer |
reference |
| any "My Festival" campaign work (#411/#413/#414/#415, cloud sync) | my-festival-campaign |
docs/** taxonomy, ADRs, issue/commit/PR house style, completion summaries |
docs-and-writing |
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 · 597 lines · 8,182 tokens per session scan A cb9b790e2648
cambridge-beer-festival-app AGENTS.md is an instructions file published in the GitHub repository richardthe3rd/cambridge-beer-festival-app (3 stars, last pushed today), licensed MIT. It adds 8,182 tokens to every session, about $0.0327 per session on Opus 5.5. 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.
cambridge-beer-festival-app AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cambridge-beer-festival-app AGENTS.mdrichardthe3rd/cambridge-beer-festival-app | Instructions file | 3 | today | MIT | A | 8,182 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |