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 skills/98ping/chip/canvas-quiznpx skills add 98ping/chip --skill canvas-quizgit clone --depth 1 https://github.com/98ping/chipWrote 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/skills/98ping/chip/canvas-quiz)<a href="https://agentmods.dev/skills/98ping/chip/canvas-quiz"><img src="https://agentmods.dev/badge/skills/98ping/chip/canvas-quiz.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 | $0.00117 | $0.01000 |
| Opus 5 | $0.00059 | $0.00500 |
| Sonnet 5 | $0.00023 | $0.00200 |
| Haiku 4.5 | $0.00012 | $0.00100 |
Grade A, and why
canvas-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 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas quizzes
Drives a Canvas Classic Quiz end to end with the Claude in Chrome tools. The
full runbook — every trap, with the fix — is tooling/CANVAS_QUIZZES.md.
Read it before the first interaction; what follows is the shape of the job.
The page helper is tooling/canvas-quiz.js, the CLI is
scripts/canvas-quiz.mjs.
Which runbook
Check the assignment's submission_types:
["online_quiz"]+ aquiz_id→ this skill.["external_tool"]at myopenmath.com →myopenmathskill. Different machinery entirely (LTI iframe, MathQuill, per-question submits).
Ask first
Three separate asks, and they do not imply each other:
- Opening the attempt — the one people underestimate. On a 1-attempt or
timed quiz this is the irreversible step, not the submit. Always check
infofirst and quote the numbers when you ask. - Typing answers.
- Submitting. Never on your own initiative.
Never enter credentials anywhere.
Steps
-
Find it —
node scripts/canvas-quiz.mjs list <courseId>. The/quizzesAPI index is disabled on many courses; this walks assignments instead, which always works. -
Pre-flight —
node scripts/canvas-quiz.mjs info <courseId> <quizId>andattempts <courseId> <quizId>. Readallowed_attemptsandtime_limitout loud before doing anything. A timed quiz means the clock runs while you think — plan the answers before opening it. -
Open the attempt — a real click on Take the Quiz. A
GETon/takesilently re-renders the landing page and starts nothing; it looks broken but isn't. Confirm#submit_quiz_formexists and the.display_questioncount matchesquestion_count. -
Read and save, before answering. Paste
tooling/canvas-quiz.js, call__QDUMP().javascript_tooltruncates around 1 KB — chunk viaJSON.stringify(__QDUMP()).match(/[\s\S]{1,900}/g). Thennode scripts/canvas-quiz.mjs render <dump.json> output/<name>.md.
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 · 81 lines · 117 tokens per session scan A 677c31fde118
canvas-quiz is a skill published in the GitHub repository 98ping/chip (2 stars, last pushed 10d ago), licensed MIT. It adds 117 tokens to every session and 1,000 once invoked, about $0.0006 per session on Opus 5. 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 skills, from other repositories
playwright-expert
Use when writing E2E tests with Playwright, setting up test infrastructure, or debugging flaky browser tests. Invoke for browser automation, E2E tests, Page Object Model, test flakiness, visual testing.
site-snapshot-review
Review one supported site's exported snapshot records without reopening live browser automation.
swift-study
Interactive Swift/iOS tutor with two modes. Classic explains first, Mastery uses a predict-first Core Loop with gates.
study-summary
Saves learning notes from the current conversation. Classic mode makes concise notes, Mastery mode keeps detailed training artifacts.
swift-quiz
Adaptive Swift/iOS quiz with two modes. Classic is lighter, Mastery requires mechanism-level reasoning.
laravel-dusk
Laravel Dusk - Browser automation and testing API for Laravel applications. Use when writing browser tests, automating UI testing, testing JavaScript interactions, or implementing end-to-end tests in Laravel.