qa-critical-ux

qa-critical-ux is a skill for Claude Code, Codex from fastrepl/anarlog. It costs 34 tokens per session (2,089 once invoked), scanned C, original, MIT.

A focused quality check of Anarlog’s main Pro-user journey. It covers starting the app, onboarding, permissions, sign-in, provider setup, recording microphone and computer audio, and producing an automatic summary.

In plain words
What is it for?
Use it when someone explicitly asks for QA of the Pro experience. It checks launch, onboarding, audio capture, and summary creation from a fresh start.
Why use it?
It gives a consistent check of the core journey without expanding into unrelated testing. Problems found during the check are recorded as information and do not by themselves approve or block a release.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

About the project

anarlog is a local-first AI meeting notetaker that captures device audio, transcribes meetings, and stores notes, transcripts, and recordings on the user's computer. It is for people who want meeting notes without adding a bot to calls or sending conversation data to an external cloud. The catalogue entries provide agent integrations and workflows for the application.

fastrepl/anarlog · 9,245 stars · on GitHub · anarlog.so

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/fastrepl/anarlog/qa-critical-ux
Any agent
npx skills add fastrepl/anarlog --skill qa-critical-ux
Clone the repo
git clone --depth 1 https://github.com/fastrepl/anarlog

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for qa-critical-ux

README.md
[![agentmods](https://agentmods.dev/badge/skills/fastrepl/anarlog/qa-critical-ux.svg)](https://agentmods.dev/skills/fastrepl/anarlog/qa-critical-ux)
Your own site
<a href="https://agentmods.dev/skills/fastrepl/anarlog/qa-critical-ux"><img src="https://agentmods.dev/badge/skills/fastrepl/anarlog/qa-critical-ux.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,089 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00034 $0.02089
Opus 5 $0.00017 $0.01045
Sonnet 5 $0.00007 $0.00418
Haiku 4.5 $0.00003 $0.00209

Measured 6d ago against content hash 9c5e3db040ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

qa-critical-ux scanned grade C 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 6d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/launch-native-dev-qa.sh, scripts/launch-native-dev-qa.test.mjs, scripts/resolve-gitbutler-candidate.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/Library/Application\ Support/com.hyprnote.dev # Dev
.agents/skills/qa-critical-ux/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA: Critical User Experience

This is a standalone QA workflow. Run it only when the user explicitly asks for QA; a release request alone does not invoke it. QA results do not approve or block a release.

Keep the QA scope focused on the Pro user journey, starting from onboarding:

  1. The app launches and never hangs.
  2. Onboarding completes from scratch: permissions, sign-in, provider setup.
  3. A recording captures both microphone and system audio.
  4. Stopping the recording produces an automated summary.

Everything else is outside this skill's scope. Do not expand the run because more checks are imaginable.

Out of Scope — Tracked in Linear Instead

If you hit a failure in one of these areas incidentally, record it as an informational note against the ticket and keep the requested QA focused. Do not run dedicated fixtures or matrices for them.

  • AEC quality (echo leakage, residual-echo metrics, double-talk): ANLG-98
  • Automatic speaker identification / voiceprints: ANLG-222
  • Real-world capture across devices, rooms, and live participants: ANLG-284
  • Auth callback handoff and sign-out edge cases: ANLG-285
  • Calendar connect, events, notifications: ANLG-286
  • CloudSync activity deferral, leases, transcript-integrity hashes: ANLG-287
  • On-device STT/LLM provider matrix: ANLG-288

Real-device and real-participant evaluation belongs to ANLG-284, not to this checklist.

Setup

Build and launch an authenticated native Dev bundle:

.agents/skills/qa-critical-ux/scripts/run-native-dev-qa.sh

The helper builds against the currently deployed production public configuration (VITE_APP_URL, VITE_API_URL, VITE_SUPABASE_URL, VITE_SUPABASE_ANON_KEY must match production; local URLs cannot pass), uses its own persistent Cargo cache under ~/Library/Caches/anarlog (never the repo target directory), and launches with AUDIO_SYNC_PROBE=1 and LISTENER_DEBUG=1. It launches the .app through LaunchServices so macOS evaluates process-scoped permissions against the bundle identity. Do not run the executable under Contents/MacOS directly. Reuse an already-current bundle with --launch-only.

Read the full file on GitHub · 200 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago First seen · 200 lines · 34 tokens per session scan C 9c5e3db040ad

Subscribe to this mod's changes

qa-critical-ux is a skill published in the GitHub repository fastrepl/anarlog (9,245 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 2,089 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

add-ai-feature-policy

Use when adding a new deck-aware AI feature (DeckFeatures axis) and its companion policies (TacticalPolicy + optional MulliganPolicy) to phase-ai. Codifies the structural-detection pattern, AST-type locations, parts-based predicate convention, registry wiring sites, and recurring review traps so a new feature ships in…

phase-rs/phase · 81 tokens

engine-implementer

End-to-end phase.rs implementation pipeline: plan, review-plan, implement, review-impl, commit — each step run in a fresh spawned agent, with automatic phase decomposition for oversized workloads.

phase-rs/phase · 43 tokens

add-engine-effect

Use when adding a new effect, mechanic, or parser capability to the engine. Covers the full lifecycle from types → parser → resolver → targeting → frontend → AI → tests.

phase-rs/phase · 39 tokens

add-interactive-effect

Use when adding any effect or ability that requires player input mid-resolution — choices, selections, modal decisions, or any WaitingFor/GameAction round-trip. Covers the continuation pattern, engine handler wiring, AI legal actions, multiplayer routing, and frontend UI.

phase-rs/phase · 55 tokens

casting-stack-conditions

Use when modifying the casting flow, stack resolution, condition systems, WaitingFor/GameAction state machine, or adding optional costs, new casting steps, or conditional ability resolution.

phase-rs/phase · 39 tokens

unlock-set

Unlock the majority of a Magic set's unsupported cards by clustering missing parser/engine primitives, briefing the engine-implementer skill tier-by-tier, and committing between clusters. Use when the user asks to "unlock the [SET] cards", "improve coverage for [SET]", or requests highest-ROI coverage work on a…

phase-rs/phase · 103 tokens