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 sliamh11/Deus --skill quiz-megit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/sliamh11/deus/quiz-me)<a href="https://agentmods.dev/skills/sliamh11/deus/quiz-me"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/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/sliamh11/deus/quiz-me"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/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 Rogue Agent · line 14 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.03219 |
| Opus 5 | $0.00041 | $0.01610 |
| Sonnet 5 | $0.00016 | $0.00644 |
| Haiku 4.5 | $0.00008 | $0.00322 |
Grade A, and why
quiz-me 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 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.
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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/quiz-me — quiz the user on what was just built
Adapted from the MIT-licensed no-numb plugin (github.com/Ciucky/no-numb); see
.claude/skills/ATTRIBUTION-no-numb.md. Runs host-side.
Overview
After you write code for someone, they usually understand the result at a high level — what it does, its inputs and outputs — but not the internals or the why. That understanding "vaporizes." This skill has you administer a short comprehension quiz on what you just did this turn, so the understanding sticks. Being tested is itself the learning (retrieval practice); the quiz is not just a check.
Core principle: quiz what this turn produced, from your own memory of what you just did — not generic trivia, not the whole codebase, not what the app does at a high level.
When to run
- Right after a turn in which you edited or wrote files, before finishing.
- When the user runs
/quiz-me. - When the no-numb Stop hook (
.claude/hooks/nonumb-gate.sh) blocks your turn and asks you to quiz. (That gate is DEFAULT-OFF; it fires only when the user has opted in viaDEUS_NONUMBor~/.config/deus/nonumb.json.)
Step 1 — Is it worth quizzing?
Look at what you changed this turn. Bias toward quizzing. Only skip when the change is genuinely cosmetic: formatting / whitespace, a variable rename, a CSS color tweak, a typo fix, a version bump. Everything else → quiz. When in doubt, quiz. If you do skip, say so in one line and stop — don't quiz on nothing.
Step 2 — Read the settings
Read ~/.config/deus/nonumb.json. Keys (all optional, defaults in parentheses):
| Key | Meaning |
|---|---|
depth ("standard") |
"standard" / "deep" / "principle" — the retrieval-difficulty dial below. |
grader ("independent") |
"independent" = a blind GPT/codex backend authors the quiz (Step 2b); "self" = you author it from your own memory of the turn (skip Step 2b). |
grader_model (codex default) |
optional faster codex model id for the author backend. |
grader_reasoning ("low") |
codex reasoning effort for authoring — low keeps the gate snappy. |
grader_timeout_s (120) |
author backend timeout. |
cards.enabled (true) |
persist a learning card after a pass (Step 7). |
cards.dir ("Learning-Cards") |
vault-relative card directory. |
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.
- 5d ago First seen · 234 lines · 81 tokens per session scan A 4e331af36b2c
quiz-me is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 3,219 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
Research for Datacore
Automated research — source processing, podcast generation, and knowledge extraction.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
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…
prompts-chat
Use when searching, installing, or improving AI skills and prompts via prompts.chat or skills.sh. Triggers on skill search, prompt lookup, install skill, improve prompt, prompts.chat.
talk-stage1-extract
Extracts and structures source material (articles, transcripts, notes) into a talk summary with narrative arc, themes, metrics, and gaps. Auto-detects REX vs Concept type. Use when starting a new talk from any source material or auditing existing material before committing to a talk.
talk-stage3-concepts
Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest…