Borrowing it
Nothing to install: this file belongs to aviraldua93/architect-ai. 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/aviraldua93/architect-ai/main/.claude/commands/quiz.mdgit clone --depth 1 https://github.com/aviraldua93/architect-aiWrote 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/commands/aviraldua93/architect-ai/quiz)<a href="https://agentmods.dev/commands/aviraldua93/architect-ai/quiz"><img src="https://agentmods.dev/badge/commands/aviraldua93/architect-ai/quiz/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/commands/aviraldua93/architect-ai/quiz"><img src="https://agentmods.dev/badge/commands/aviraldua93/architect-ai/quiz.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 | $0.00000 | $0.00641 |
| Opus 5 | $0.00000 | $0.00320 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
quiz 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 9d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quiz
Run a practice quiz for the Claude Certified Architect exam.
Usage
/quiz — Random questions across all domains
/quiz 1 — Domain 1: Agentic Architecture & Orchestration
/quiz 1.3 — Task Statement 1.3: Subagent Invocation
/quiz 2 — Domain 2: Tool Design & MCP Integration
/quiz 3 — Domain 3: Claude Code Configuration & Workflows
/quiz 4 — Domain 4: Prompt Engineering & Structured Output
/quiz 5 — Domain 5: Context Management & Reliability
What It Does
- Loads questions from
src/content/questions/JSON files - Filters by the domain or task statement you specify (if any)
- Presents each question with a scenario, four options, and an explanation
- Tracks your score and shows a breakdown by domain at the end
Running Directly
You can also run the quiz from the terminal:
npx tsx src/cli/index.ts quiz # All domains
npx tsx src/cli/index.ts quiz -d 1 # Domain 1 only
npx tsx src/cli/index.ts quiz -t 1.3 # Task Statement 1.3 only
Domains & Task Statements
| Domain | Name | Key Task Statements |
|---|---|---|
| 1 | Agentic Architecture & Orchestration | 1.1 Agentic Loops, 1.2 Multi-Agent Orchestration, 1.3 Subagent Invocation, 1.4 Workflow Enforcement, 1.5 Agent SDK Hooks, 1.6 Task Decomposition, 1.7 Session State |
| 2 | Tool Design & MCP Integration | 2.1 Tool Descriptions as Selection Mechanism, 2.2 Structured Error Responses, 2.3 Tool Choice Modes, 2.4 MCP Resources, Tools & Prompts, 2.5 Built-in vs Custom Tools |
| 3 | Claude Code Configuration & Workflows | 3.1 CLAUDE.md Hierarchy, 3.2 Slash Commands & Skills, 3.3 Path Rules with Glob Patterns, 3.4 Plan Mode Workflow, 3.5 Iterative Refinement, 3.6 CI/CD Integration |
| 4 | Prompt Engineering & Structured Output | 4.1 Explicit Criteria & Rubrics, 4.2 Few-Shot Examples, 4.3 Tool Use Schemas & Validation, 4.4 Validation-Retry Pattern, 4.5 Batch API, 4.6 Multi-Instance Review & Aggregation |
| 5 | Context Management & Reliability | 5.1 Context Preservation & Summarisation, 5.2 Escalation Patterns & Confidence, 5.3 Error Propagation in Multi-Agent Systems, 5.4 Codebase Exploration Strategies, 5.5 Human-in-the-Loop & Approval Gates, 5.6 Provenance & Audit Trails |
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.
- 9d ago First seen · 43 lines · 0 tokens per session scan A d9159d80439d
quiz is a command published in the GitHub repository aviraldua93/architect-ai (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 641 tokens. 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 commands, from other repositories
learn
Learn new capabilities through experimentation, then codify into the system.
ccc-compound
Post-task learning capture — extract patterns, corrections, and decisions to compound productivity.
explain
Explain the subject in depth using the fixed four-part structure: What, Why, Example, Consequences. Treat the subject as the thing to be explained, not as a literal question.
interview
Prepare for the interview from the filed application — predicted questions, STAR answers from real evidence, and gap-defence.
learn
Capture a reusable learning from this session — with a dedup + Save/Absorb/Drop gate so the knowledge base stays clean.
explain
Generate an interactive one-module explainer for a topic — Riko gathers code scope, Senku plans a 3-5 screen teaching arc, Speedwagon authors the HTML, assembler produces explain-out/index.html.