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 hiendinhngoc/unknowns --skill merge-quizgit clone --depth 1 https://github.com/hiendinhngoc/unknownsWrote 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/hiendinhngoc/unknowns/merge-quiz)<a href="https://agentmods.dev/skills/hiendinhngoc/unknowns/merge-quiz"><img src="https://agentmods.dev/badge/skills/hiendinhngoc/unknowns/merge-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.
<a href="https://agentmods.dev/skills/hiendinhngoc/unknowns/merge-quiz"><img src="https://agentmods.dev/badge/skills/hiendinhngoc/unknowns/merge-quiz.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.00847 |
| Opus 5 | $0.00028 | $0.00424 |
| Sonnet 5 | $0.00011 | $0.00169 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
merge-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 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.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Readiness Quiz
Before shipping, verify the HUMAN understands what's being merged. The quiz tests the user, not Claude.
Process
- Resolve the base deterministically. Prefer, in order: the base explicitly
named by the user; the current branch's configured upstream; the remote
default branch from
refs/remotes/origin/HEAD; then an existing localmainormaster. Verify the candidate withgit rev-parse --verifybefore using it. If no candidate exists, ask for a base ref and stop. - Gather the material.
- Diff:
git diff <base>...HEAD. If it is empty, also checkgit diff <base>..HEAD, tracked worktree changes, and relevant untracked files reported bygit status --short. State exactly which material was selected. If all are empty, stop because there is nothing to quiz. - Exclude generated files (lockfiles,
*.pbxproj, build outputs, vendored code) from quiz material — churn there is noise, not comprehension risk. - Deviation log: prefer files for the current branch/task slug. If task identity is unavailable, include only deviation files changed in the diff; do not sweep unrelated logs by date.
- Diff:
- Pick the 3–5 riskiest spots. If the diff is too small for 3 real questions, ask fewer and say why. First name what "dangerous" means in THIS codebase's domain — auth/money/deletion/migrations in a backend; lifecycle, state loss, and accessibility regressions in a UI app; loss/duplication/ ordering in a pipeline. Then prioritize: behavior changes on those paths, deviations from the plan, error handling changes, anything irreversible.
- Quiz one question at a time using AskUserQuestion (or plain-text
multiple choice if this agent has no such tool). If no interactive user is
available, output the quiz and stop without answering for them. Each question:
- Cites the exact file:line it's about
- Asks about consequences, not trivia: "what happens if X is null here?", "why did we bypass Y?", "what breaks if this runs twice?"
- Offers 3-4 plausible answers (one correct, distractors that reflect real misunderstandings)
- Has one correct answer backed by the exact diff hunk or file:line; if no evidence exists in the diff, do not ask that question
- On a wrong or unsure answer: explain the correct answer immediately, quoting the exact diff hunk verbatim so the user can dispute it — the quiz grades the user against the agent's reading of the diff, and that reading can be wrong. If the user disputes with evidence, concede the question, correct the score, and flag the spot as review-carefully either way.
- Produce the merge-readiness note (paste-ready for the PR description):
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.
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 · 67 lines · 56 tokens per session scan A 881b0fa78649
merge-quiz is a skill published in the GitHub repository hiendinhngoc/unknowns (9 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 847 once invoked, about $0.0003 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
ck-signatures
Extract all method/property signatures from C#, TypeScript, Kotlin, and Python files using live AST parsing. Use after ck find-files has identified the relevant folder, when evaluating multiple candidate files to avoid reading full file content.
plannotator
Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and exporting or sharing Guided Reviews. Invoke when asked to use Plannotator for anything not covered by a more specific…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
agtx-review
Self-review completed work. Check for correctness, edge cases, and code quality. Write review to .agtx/review.md and stop.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…
plain-report
Use this tool only when the user explicitly asks to create a plain report.