cert-exam-generator

cert-exam-generator is a skill for Claude Code, Codex from olgun-yilmaz/ClaudeCertifiedArchitectFoundations. It costs 85 tokens per session (5,722 once invoked), scanned B, original, MIT.

A tool for creating original practice exams for the Claude Certified Architect – Foundations certification. It writes scenario-based questions and answer keys in the repository’s exam format.

In plain words
What is it for?
Use it to generate a new practice exam, save its question and answer-key files in an exam folder, and register the exam in the manifest.
Why use it?
It turns existing notes and cheat sheets into structured study material while checking that questions have one best answer and plausible alternatives.

Skill for Claude CodeCodex

Written for Claude Code and Codex: PreToolUse hook event, but also agents/openai.yaml present. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Use it to generate a new practice exam, save its question and answer-key files in an exam folder, and register the exam in the manifest.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/olgun-yilmaz/claudecertifiedarchitectfoundations/cert-exam-generator
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.

Any agent
npx skills add olgun-yilmaz/ClaudeCertifiedArchitectFoundations --skill cert-exam-generator
Clone the repo
git clone --depth 1 https://github.com/olgun-yilmaz/ClaudeCertifiedArchitectFoundations

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 cert-exam-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/olgun-yilmaz/claudecertifiedarchitectfoundations/cert-exam-generator/github.svg)](https://agentmods.dev/skills/olgun-yilmaz/claudecertifiedarchitectfoundations/cert-exam-generator)
Your own site
<a href="https://agentmods.dev/skills/olgun-yilmaz/claudecertifiedarchitectfoundations/cert-exam-generator"><img src="https://agentmods.dev/badge/skills/olgun-yilmaz/claudecertifiedarchitectfoundations/cert-exam-generator/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.

agentmods 80×15 button for cert-exam-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/olgun-yilmaz/claudecertifiedarchitectfoundations/cert-exam-generator"><img src="https://agentmods.dev/badge/skills/olgun-yilmaz/claudecertifiedarchitectfoundations/cert-exam-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,722 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00085 $0.05722
Opus 5 $0.00043 $0.02861
Sonnet 5 $0.00017 $0.01144
Haiku 4.5 $0.00009 $0.00572

Measured 12d ago against content hash 059bb8b67d66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

cert-exam-generator scanned grade B 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

Strengthen distractors with **real but misapplied** Claude Code / API vocabulary — `tool_choice: any` vs forced, `--max-turns`, `--continue`, `--output-format stream-json`, `AgentDefinition.prompt`, `.mcp.json` vs `~/.cl
.agents/skills/cert-exam-generator/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CCAR-F Exam Generator

Author a new practice exam for the Claude Certified Architect – Foundations certification, written directly into the repo's exam format so it opens in ExamGenerator/ExamSimulator/index.html.

You are writing exam questions that a knowledgeable candidate will study from. The bar is a real certification item: a plausible production scenario, one defensibly-best answer, and three distractors that a half-prepared candidate would seriously consider. If a question can be answered without reading the scenario — because the correct choice is the longest, the most detailed, the most qualified, or the only non-silly one — it has failed and must be rewritten. The most common way this skill fails is option-length bias: an exam where "always pick the longest choice" scores well is a broken exam, no matter how good the individual scenarios are. See the option-length parity rules in Step 4 and the word-count audit in Step 6 — both are mandatory.

When to use

Use this skill when the user asks to create, generate, or add to a CCAR-F practice exam. This skill produces exam content; it does not deliver or grade exams (that's what ExamSimulator/index.html does).

Parameters (read from the conversation)

Take the exam's parameters from what the user has said. Never assume a default exam size or domain mix — but equally, never ask about something the user already specified. Ask only for what's actually missing, once, then generate.

When either count or scope is absent from the conversation, ask for all missing parameters in one concise message so the user can answer them in one pass:

  • count — how many questions. Required. Offer 20 (short practice exam), 40 (medium-length), 60 (full-length, matching real exam size), and let the user type any other number.
  • scope — which domains/subtopics to cover, and in what proportion. Offer a weighted spread across all five domains (recommended — proportional to the blueprint weightings below) or a custom domain/subtopic focus. If they pick a custom focus without naming it, ask which domain or subtopic.

Read the full file on GitHub · 218 lines

Files

What ships with it

1 file 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. 12d ago First seen · 218 lines · 85 tokens per session scan B 059bb8b67d66

Subscribe to this mod's changes

cert-exam-generator is a skill published in the GitHub repository olgun-yilmaz/ClaudeCertifiedArchitectFoundations (5 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 5,722 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

canvas

Fetch Canvas LMS courses and assignments via API token.

NousResearch/hermes-agent · 12 tokens

rwkv-architecture

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

davila7/claude-code-templates · 72 tokens

build-interactive-explainers

A guide for building interactive explainers, calculators, and simulations driven by an executable model. Users change inputs, steps, states, or events to understand a rule or see how a process develops over time.

EverMind-AI/Raven · 102 tokens

skill-creation-walkthrough

Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…

rampstackco/claude-skills · 135 tokens

stride-analysis-patterns

Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.

sangrokjung/claude-forge · 30 tokens

blind-spot-pass

Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…

sangrokjung/claude-forge · 221 tokens