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 skills add arpitbbhayani/ape-skills --skill ape-quiz-megit clone --depth 1 https://github.com/arpitbbhayani/ape-skillsWrote 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/arpitbbhayani/ape-skills/ape-quiz-me)<a href="https://agentmods.dev/skills/arpitbbhayani/ape-skills/ape-quiz-me"><img src="https://agentmods.dev/badge/skills/arpitbbhayani/ape-skills/ape-quiz-me/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/skills/arpitbbhayani/ape-skills/ape-quiz-me"><img src="https://agentmods.dev/badge/skills/arpitbbhayani/ape-skills/ape-quiz-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 49 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00081 | $0.02298 |
| Opus 5 | $0.00041 | $0.01149 |
| Sonnet 5 | $0.00016 | $0.00460 |
| Haiku 4.5 | $0.00008 | $0.00230 |
Grade A, and why
ape-quiz-me 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **A URL**: a string starting with `http://` or `https://`. Use `WebFetch` to download the content, then strip navigation, sidebars, footers, and comments before working on the body. If the URL points to a PDF (researc How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quiz Me Skill
Tests whether you understood, not whether you can recall. You share content you claim to have read; the ape reads it, builds questions off its spine, and asks them one at a time. Wrong answers get hints that narrow the search but never contain the answer. At the end you get an honest verdict: which parts you understood, which you recited, and which you missed -- with pointers back into the source for everything you should reread.
This is the sibling of [[ape-help-me-understand]]. That skill hands you understanding; this one checks whether it took hold. The two failure modes it exists to catch: reciting (you can repeat the words but cannot answer "why" or handle a changed condition) and skimming confidence (you feel done because you reached the end).
The ape never states an answer. Not during the quiz, not in a hint, not in the verdict. For anything missed, it names where in the source the answer lives and sends you back. The source teaches; the ape only points.
What to Test
Questions come from the parts of the content that carry meaning -- the same things a good summary must preserve. Every quiz draws from these types:
- Mechanism: why the thing works, one causal step at a time. "What makes the read faster?" is answerable by recitation; "what would slow down if the lookup moved back onto the request path?" is not.
- Caveat: the condition under which the central claim stops being true. If the source says X holds only when Y, there is a question about Y.
- Number: the figure that carries the claim. The exact value is not required -- the right order of magnitude and the right direction is. Knowing it was "2.4x faster" matters less than knowing it was "a couple x, not twenty".
- Transfer: change one condition and ask what happens now. This is the recited-vs-understood detector; no sentence in the source answers it, only the mechanism does.
- Trap: a plausible-sounding but wrong one-line summary of the content. The question is "what is wrong with this statement?" It catches readers who absorbed the vibe and lost the substance.
- Trade-off: what was given up to get what was gained. If the source paid a price, there is a question about the price.
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.
- 12d ago First seen · 134 lines · 81 tokens per session scan A 4e822c4b3399
ape-quiz-me is a skill published in the GitHub repository arpitbbhayani/ape-skills (40 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 2,298 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
explain-this
Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findings report. Use when the user asks to "explain this", "what am I being asked", "what's happening right now", "help me understand this", "what does…
understand-change
Teach the user to deeply understand a change through interactive tutoring: restating understanding, drilling into why/what/how, and quizzing until mastery. The active counterpart to a one-shot explanation. Use when the user asks to "understand this change", "teach me this change", "help me understand what changed"…
cizhuan-mudiban-xuangou-zhinan
A Chinese-language knowledge guide about choosing and installing ceramic tiles and wood flooring.
diaoding-zhuangxiu-zhinan
A Chinese-language knowledge guide for planning ceiling work during a home renovation, including materials, measurements, bathroom and kitchen ceilings, and living-room designs.
jiadian-bikeng-zhinan
A Chinese-language guide to choosing and installing household appliances, including kitchen, cooling, heating, water, cleaning, entertainment, and bathroom equipment.