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/.github/skills/code-review/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/code-review)<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/code-review"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/code-review/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/code-review"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/code-review.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 | $0.00162 | $0.03034 |
| Opus 5 | $0.00081 | $0.01517 |
| Sonnet 5 | $0.00032 | $0.00607 |
| Haiku 4.5 | $0.00016 | $0.00303 |
Grade A, and why
code-review 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 11d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing the Cambridge Beer Festival app
This repository's automated reviews have a single dominant failure mode: syntax and type claims made against an outdated mental model of Dart. Every "this will fail to compile" comment posted here so far has been wrong, and each one cost a maintainer a round-trip to refute.
This skill exists to stop that. Read it before writing any comment about a
.dart file.
The codebase is overwhelmingly Dart/Flutter, so §§1–5 are Dart-specific. The
rest applies to every file: §2 (CI is ground truth), §6 (what is worth
reviewing), §7 (settled decisions), and §8 (comment hygiene). The TypeScript
and JavaScript under cloudflare-worker/, functions/, and scripts/ is
covered by its own vitest suites and Prettier — §2 holds there too.
1. Look up the language version before you judge syntax
Read it from the source. Do not trust a version restated in prose — including anywhere in this file.
| What | File | Look for |
|---|---|---|
| Dart SDK constraint | pubspec.yaml |
environment: → sdk: |
| Flutter version | mise.toml |
flutter = "…" |
Everything the Dart language gained up to and including that floor is available and in active use here. Check the floor against the feature table in §4 before calling anything a syntax error.
If a construct looks unfamiliar, the overwhelmingly likely explanation is that it is a language feature newer than your prior, not a bug. This repository has tracked recent Flutter releases closely — an outdated assumption about the version is the single most common cause of a wrong review comment here.
2. The rule that outranks every other rule in this skill
CI compiles this code before you review it.
./bin/mise run check runs generate → analyze → test. The analyze job runs
flutter analyze without --no-fatal-infos, so every diagnostic — error,
warning, and info — fails the build. The test job runs the full suite (1300+
tests).
Therefore: if the checks are green, the code compiles. A comment asserting otherwise is not a finding, it is a false positive. Do not post it. There is no phrasing of "this should fail to compile" that is useful on a green commit — verify against the checks first, and if they pass, review something else.
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.
- 11d ago First seen · 215 lines · 162 tokens per session scan A 303eaea5022b
code-review is a skill published in the GitHub repository richardthe3rd/cambridge-beer-festival-app (2 stars, last pushed yesterday), licensed MIT. It adds 162 tokens to every session and 3,034 once invoked, about $0.0008 per session on Opus 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…