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/failure-archaeology/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/failure-archaeology)<a href="https://agentmods.dev/skills/richardthe3rd/cambridge-beer-festival-app/failure-archaeology"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/failure-archaeology/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/failure-archaeology"><img src="https://agentmods.dev/badge/skills/richardthe3rd/cambridge-beer-festival-app/failure-archaeology.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 | $0.00214 | $0.11058 |
| Opus 5 | $0.00107 | $0.05529 |
| Sonnet 5 | $0.00043 | $0.02212 |
| Haiku 4.5 | $0.00021 | $0.01106 |
Grade A, and why
failure-archaeology 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 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.
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 — 749 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Failure Archaeology
This is the chronicle. Every row below is a closed (or explicitly still-open) investigation: what broke, why, the evidence trail (issue/PR/SHA/file:line), its final status, and the one-sentence lesson to carry forward. It exists so an agent with zero context doesn't spend a review cycle re-proposing a fix that was already tried and rejected, or re-breaking something that was already hardened.
Entry format (strict): Symptom → Root cause → Evidence → Status → Lesson.
Status vocabulary:
fixed-in— landed, cite the PR/SHA/commit message.rejected-because— proposed, explicitly turned down, with the reason.still-open— known, not yet fixed; check before assuming it's new.
All PR/issue numbers and SHAs below were checked against git log and the working
tree on 2026-07-02. The local clone is shallow (~50 commits) — anything with a
SHA was verified directly; older items are cited by PR/issue number only (correct
per GitHub, not re-derivable from git log here).
1. State management (BeerProvider & domain controllers)
Rapid festival switch races the drinks fetch
- Symptom → switching festivals quickly showed the previous festival's
drinks; a slow in-flight
loadDrinks()overwrote the newer festival's data. - Root cause → concurrent
loadDrinks()calls, no cancellation token; the older completion clobbered newer state. - Evidence → PR #263 (discard stale drinks responses); PR #275 added the
_drinksLoadTokenguard (Fixes #266). Guard checked atlib/providers/beer_provider.dart:480,495,519today (_refreshDrinksFromNetwork). - Status → fixed-in #275, still enforced.
- Lesson → any async load keyed to a mutable "current selection" needs a
monotonic token;
awaitalone cannot cancel an orphaned future.
_currentFestival reference goes stale after a background registry refresh
- Symptom → a server-side change to a festival's
availableBeverageTypes(e.g. cider added) silently never loaded for the session. - Root cause →
initialize()seeds_currentFestivalfrom cache, firesunawaited(loadFestivals()); the success branch only reassigned_currentFestivalwhen it was null, so the stale cachedFestivalobject stayed referenced while in-flightloadDrinksused its old types. - Evidence → issue #306 (priority:high); fixed by PR #362.
- Status → fixed-in #362.
- Lesson → when a background refresh replaces a collection, re-resolve any held reference into the new collection by domain key, not identity.
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 · 749 lines · 214 tokens per session scan A 28649f5ebaa5
failure-archaeology is a skill published in the GitHub repository richardthe3rd/cambridge-beer-festival-app (2 stars, last pushed yesterday), licensed MIT. It adds 214 tokens to every session and 11,058 once invoked, about $0.0011 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
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.