agentmods.dev

project-quiz

project-quiz is a skill for Claude Code from Ruisi-Lu/github-loop-engineering-skill. It costs 71 tokens per session (1,615 once invoked), scanned A, original, MIT.

A read-only quiz built from a repository's merged pull requests and related issues. Pull requests are records of accepted changes, their reasons, rejected alternatives, and bugs that influenced the project.

In plain words
What is it for?
It is for teaching contributors how a project works by asking questions about its past changes through the connected GitHub service.
Why use it?
It helps newcomers learn a codebase's history without reading every change themselves. Each answer receives an explanation, so the quiz teaches rather than grades.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the github-loop-engineering plugin — 2 skills shipped together

not rated 8repo yesterday A scan 71 tokens original MIT

Good fit It is for teaching contributors how a project works by asking questions about its past changes through the connected GitHub service.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruisi-lu/github-loop-engineering-skill/project-quiz
View source ↗ Ruisi-Lu/github-loop-engineering-skill
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 Ruisi-Lu/github-loop-engineering-skill --skill project-quiz
Clone the repo
git clone --depth 1 https://github.com/Ruisi-Lu/github-loop-engineering-skill

Made for: Claude Code.

Or install github-loop-engineering, the plugin that ships this one along with the rest of its 2 skills.

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 project-quiz

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruisi-lu/github-loop-engineering-skill/project-quiz/github.svg)](https://agentmods.dev/skills/ruisi-lu/github-loop-engineering-skill/project-quiz)
Your own site
<a href="https://agentmods.dev/skills/ruisi-lu/github-loop-engineering-skill/project-quiz"><img src="https://agentmods.dev/badge/skills/ruisi-lu/github-loop-engineering-skill/project-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.

agentmods 80×15 button for project-quiz

Your own site · 80×15
<a href="https://agentmods.dev/skills/ruisi-lu/github-loop-engineering-skill/project-quiz"><img src="https://agentmods.dev/badge/skills/ruisi-lu/github-loop-engineering-skill/project-quiz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,615 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00071 $0.01615
Opus 5.5 $0.00028 $0.00646
Sonnet 5.5 $0.00014 $0.00323
Haiku 4.5 $0.00007 $0.00161

Measured 5d ago against content hash f1bfa2fa905a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-quiz scanned grade A 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. Read GitHub only through the connected GitHub MCP server. Don't fall back to `gh`, `curl`, direct REST, or handwritten GraphQL. If no GitHub MCP server is connected, or it can't read pull requests, stop and say which
skills/project-quiz/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project quiz

Turn a repository's pull request history into a short quiz that teaches the project. Merged pull requests record what changed, why, which alternatives were rejected, and which bugs shaped the current design. Reading them all is slow, so you read them, pick what a collaborator most needs to know, and ask about it. Every answer, right or wrong, is followed by a short explanation with the pull request it came from.

The quiz is for learning, not for grading. A wrong answer means the next explanation matters, never that the user failed.

Rules

  1. Start only when the user invokes this skill or explicitly asks for a project quiz. Never start one as a side effect of other work.
  2. Read GitHub only through the connected GitHub MCP server. Don't fall back to gh, curl, direct REST, or handwritten GraphQL. If no GitHub MCP server is connected, or it can't read pull requests, stop and say which toolset or permission is missing. The pull_requests, issues, and repos toolsets cover everything this skill reads.
  3. Write nothing to GitHub: no comments, labels, issues, or reviews. The quiz stays in the conversation. Save it to a local file only when the user asks, at a path they choose.
  4. Ground every question in evidence you read: a pull request, its closing issues, its review discussion, or the current code. Never invent a reason a pull request doesn't state. When the history doesn't say why, ask about what changed, not why.
  5. Leave people out. Don't ask who wrote, reviewed, or merged something, and don't judge anyone's work.
  6. Never put a secret, credential, internal hostname, or personal data from a diff or discussion into a question or an explanation, even in a private repository.

1. Settle the scope

Take the scope from the invocation's arguments and the conversation. Use these defaults for anything not given, and don't ask about them:

  • Repository: the current repository, from the git remote or the conversation. When more than one is plausible, ask one question.
  • Questions: 8.
  • Range: the most recently merged pull requests, as many as you need to find enough material. Go back further when recent history is mostly routine.
  • Area: the whole project, unless the user names a directory, component, label, or date range.
  • Language: the user's language. Keep code, commands, and identifiers as they are.

Read the full file on GitHub · 80 lines

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. 5d ago First seen · 80 lines · 71 tokens per session scan A f1bfa2fa905a

Subscribe to this mod's changes

project-quiz is a skill published in the GitHub repository Ruisi-Lu/github-loop-engineering-skill (8 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,615 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-01.

CommitsGit and workflowLearning and teachingagent-skillsagentic-codingai-agentsgithub-mcpgithub-projectsloop-engineering
Related

project-quiz compared with skills from other repositories

project-quiz next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
project-quizRuisi-Lu/github-loop-engineering-skillSkill8yesterdayMITA71Claude Code
moai-ref-git-workflowmodu-ai/moai-adkSkill1.3k4d agoApache-2.0A58Claude Code
request-apexyard-featureme2resh/apexyardSkill542yesterdayMITA47Claude Code
changelogwesammustafa/Claude-Code-Everything-You-Need-to-KnowSkill3.5k3d agononeA28Claude Code
git-workflowNPC-Worldwide/npcshSkill5023d agoMITA0Claude Code, Codex
signing-preflightavelikiy/great_ctoSkill1122d agoMITA105Claude Code
validate-changesFlorianBruniaux/claude-code-ultimate-guideSkill6.4k2d agoCC-BY-SA-4.0A16Claude Code