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/proof-and-analysis-toolkit/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/proof-and-analysis-toolkit)<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/proof-and-analysis-toolkit"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/proof-and-analysis-toolkit/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/proof-and-analysis-toolkit"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/proof-and-analysis-toolkit.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 | $0.00216 | $0.06472 |
| Opus 5 | $0.00108 | $0.03236 |
| Sonnet 5 | $0.00043 | $0.01294 |
| Haiku 4.5 | $0.00022 | $0.00647 |
Grade A, and why
proof-and-analysis-toolkit 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.
description: First-principles analysis recipes for the Cambridge Beer Festival app — "prove it, don't just install it." Load before trusting or changing API-field parsing/schema code, before building the proof/forensic m How it starts
The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proof and Analysis Toolkit
Doctrine: a claim about this codebase is not true because it sounds plausible, because a doc says so, or because a past PR title implies it — it is true because you counted, decoded, or modeled it yourself and the numbers came out the way your model predicted. Every recipe below ends in a number, a matched frame, or a written prediction that either held or didn't — never in "should be fine."
Six recipes. Each has: when to use, steps, a worked example from this repo's real
history (issue/PR numbers you can hand to gh issue view or grep the CHANGELOG for),
and what counts as proof.
Recipe 1 — Empirical data census
When to use: before writing or trusting any fromJson branch, before believing a
claim like "field X is always a string," before changing a status/enum mapping, or
before filing a bug that assumes one festival's data shape applies to all festivals.
Why it matters here: the live feeds at data.cambeerfestival.app are described in
AGENTS.md as having type-union fields (abv, allergens, year_founded, bar) — but a union
described in prose can silently be wrong, incomplete, or stale. The only way to know
what a field actually does is to fetch every festival/category combination and count.
Steps
- List the categories to check:
beer, cider, perry, mead, wine, international-beer, low-no, apple-juice(seelib/models/beverage_categories.dart), scoped to whichever festival(s) matter — checkavailable_beverage_typesindata/festivals.jsonfirst, since per-festival unions differ (a winter festival may omit categories a summer one has, or use different vocabulary in free-text fields). - Fetch each
{festivalId}/{category}.json— the shape is{"producers": [...], "timestamp": ...}, NOT a bare array (verify this before assuming the top-level type; seelib/services/beer_api_service.dart:110-127,parseProducers). - Run a
jq group_by(type)census over every field you're about to parse or change. - Compare across at least two festivals from different seasons before concluding a union is "always X" — a summer-only sample under-counts winter-only vocabulary (or vice versa).
- State the conclusion as a fraction, never a vibe: "branch X fires in N/M records" or "never fires in N/M records — candidate dead code" or "genuinely mixed — keep the branch."
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 · 440 lines · 216 tokens per session scan A ac417a9bb3d9
proof-and-analysis-toolkit is a skill published in the GitHub repository richardthe3rd/cambridge-beer-festival-app (2 stars, last pushed yesterday), licensed MIT. It adds 216 tokens to every session and 6,472 once invoked, about $0.0011 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.