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.
npx agentmods add rules/moclam1905/cocktailrecipes/qa-mode-mapgit clone --depth 1 https://github.com/moclam1905/CocktailRecipesWrote 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/rules/moclam1905/cocktailrecipes/qa-mode-map)<a href="https://agentmods.dev/rules/moclam1905/cocktailrecipes/qa-mode-map"><img src="https://agentmods.dev/badge/rules/moclam1905/cocktailrecipes/qa-mode-map.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.04645 |
| Opus 5 | $0.00000 | $0.02322 |
| Sonnet 5 | $0.00000 | $0.00929 |
| Haiku 4.5 | $0.00000 | $0.00464 |
Grade A, and why
qa-mode-map 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 4d 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.
This is a copy
100% identical to qa-mode-map — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 495 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TL;DR: This enhanced QA mode provides comprehensive validation at any stage of development. It automatically detects the current phase, validates Memory Bank consistency, verifies task tracking, and performs phase-specific technical validation to ensure project quality throughout the development lifecycle.
🔍 ENHANCED QA MODE PROCESS FLOW
graph TD
Start["🚀 START QA MODE"] --> DetectPhase["🧭 PHASE DETECTION<br>Determine current project phase"]
%% Phase detection decision path
DetectPhase --> PhaseDetermination{"Current Phase?"}
PhaseDetermination -->|"VAN"| VANChecks["VAN Phase Validation"]
PhaseDetermination -->|"PLAN"| PLANChecks["PLAN Phase Validation"]
PhaseDetermination -->|"CREATIVE"| CREATIVEChecks["CREATIVE Phase Validation"]
PhaseDetermination -->|"IMPLEMENT"| IMPLEMENTChecks["IMPLEMENT Phase Validation"]
%% Universal checks that apply to all phases
DetectPhase --> UniversalChecks["🔍 UNIVERSAL VALIDATION"]
UniversalChecks --> MemoryBankCheck["1️⃣ MEMORY BANK VERIFICATION<br>Check consistency & updates"]
MemoryBankCheck --> TaskTrackingCheck["2️⃣ TASK TRACKING VERIFICATION<br>Validate tasks.md as source of truth"]
TaskTrackingCheck --> ReferenceCheck["3️⃣ REFERENCE VALIDATION<br>Verify cross-references between docs"]
%% Phase-specific validations feed into comprehensive report
VANChecks & PLANChecks & CREATIVEChecks & IMPLEMENTChecks --> PhaseSpecificResults["Phase-Specific Results"]
ReferenceCheck & PhaseSpecificResults --> ValidationResults{"✅ All Checks<br>Passed?"}
%% Results Processing
ValidationResults -->|"Yes"| SuccessReport["📝 GENERATE SUCCESS REPORT<br>All validations passed"]
ValidationResults -->|"No"| FailureReport["⚠️ GENERATE FAILURE REPORT<br>With specific fix instructions"]
%% Success Path
SuccessReport --> UpdateMB["📚 Update Memory Bank<br>Record successful validation"]
UpdateMB --> ContinueProcess["🚦 CONTINUE: Phase processes<br>can proceed"]
%% Failure Path
FailureReport --> IdentifyFixes["🔧 IDENTIFY REQUIRED FIXES"]
IdentifyFixes --> ApplyFixes["🛠️ APPLY FIXES"]
ApplyFixes --> Revalidate["🔄 Re-run validation"]
Revalidate --> ValidationResults
%% Style nodes for clarity
style Start fill:#4da6ff,stroke:#0066cc,color:white
style DetectPhase fill:#f6ad55,stroke:#c27022,color:white
style UniversalChecks fill:#f6546a,stroke:#c30052,color:white
style MemoryBankCheck fill:#10b981,stroke:#059669,color:white
style TaskTrackingCheck fill:#10b981,stroke:#059669,color:white
style ReferenceCheck fill:#10b981,stroke:#059669,color:white
style ValidationResults fill:#f6546a,stroke:#c30052,color:white
style SuccessReport fill:#10b981,stroke:#059669,color:white
style FailureReport fill:#f6ad55,stroke:#c27022,color:white
style ContinueProcess fill:#10b981,stroke:#059669,color:white,stroke-width:2px
style IdentifyFixes fill:#f6ad55,stroke:#c27022,color:white
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.
- 4d ago First seen · 495 lines · 0 tokens per session scan A 15ab41c16149
qa-mode-map is a cursor rule published in the GitHub repository moclam1905/CocktailRecipes (1 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,645 tokens. A static security scan graded it A with 0 findings. It is 100% identical to qa-mode-map, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
android-project
Core behavior rules for AI agents working on this Android project.
ios-project-bootstrap
Walks a developer through bootstrapping a BRAND-NEW iOS project for agentic CLI delivery — Apple Developer Program enrollment, App Store Connect listing, provisioning profiles, Fastlane setup from scratch, Firebase App Distribution, TestFlight + App Store first upload. Use when the user says they're starting a new iOS…
android-project-bootstrap
Walks a developer through bootstrapping a BRAND-NEW Android project for agentic CLI delivery — creating the Firebase project, registering the Android app, setting up App Distribution, creating the Google Play Console listing, wiring API access, and installing the Gradle plugins. Use when the user says they're starting…
android-project-onboarding
Walks a new developer through one-time setup of an EXISTING configured Android project from a blank macOS install — JDK, Android SDK, AVD, scrcpy, shell env vars, credential files, and a smoke-test build. Assumes Firebase project + Play Console listing already exist; user just needs to acquire credentials. Use when…
ios-project-onboarding
Walks a new developer through one-time setup of an EXISTING configured iOS project from a blank macOS install — Xcode, Fastlane, SPM dependencies, code signing, simulator, and a smoke-test build. Assumes App Store Connect + Firebase + Fastlane are already configured upstream; user just needs local toolchain +…
ios-project
Core behavior rules for AI agents working on this iOS project.