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 quranpedia/qurantech-skill --skill qurantechgit clone --depth 1 https://github.com/quranpedia/qurantech-skillWrote 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/quranpedia/qurantech-skill/qurantech)<a href="https://agentmods.dev/skills/quranpedia/qurantech-skill/qurantech"><img src="https://agentmods.dev/badge/skills/quranpedia/qurantech-skill/qurantech/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/quranpedia/qurantech-skill/qurantech"><img src="https://agentmods.dev/badge/skills/quranpedia/qurantech-skill/qurantech.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 | $0.00264 | $0.01921 |
| Opus 5 | $0.00132 | $0.00960 |
| Sonnet 5 | $0.00053 | $0.00384 |
| Haiku 4.5 | $0.00026 | $0.00192 |
Grade A, and why
qurantech 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QuranTech
Build Quran apps and tools with best practices, verified data sources, and respect for the sacred text.
Interactive Workflow
Clarify requirements before building or modifying anything — these decisions change the architecture, and reworking a Quran app after picking the wrong qira'a or data source is expensive. Use AskUserQuestion where available; otherwise ask in plain conversation. Skip questions the user has already answered, and skip the interview entirely when the request is fully specified.
For new projects
Ask these questions in sequence (1-4 per round):
- What are you building? (Mushaf reader, audio app, learning tool, API, search engine, etc.)
- Target platform? (Web, iOS, Android, Flutter, backend API, etc.)
- Which qira'a? (Hafs only, Warsh, multiple, all 10 — see references/qiraat.md)
- Core features needed? (Audio, tajweed, search, translations, tafsir, memorization, mushaf pages)
- Offline support? (Bundled data, download-on-demand, online-only)
- Data sources? Guide them through API options (see references/api-comparison.md)
After gathering answers, recommend an architecture and data sources, then proceed.
For existing projects
Ask:
- What feature are you adding/changing?
- What's the current tech stack?
- What qira'a does the app currently support?
- What data sources are currently in use?
Then consult the relevant reference file and guide the implementation.
Adab Rules (Mandatory)
Read and enforce references/adab.md at all times. These rules are non-negotiable:
- Never truncate an ayah mid-text
- Never strip diacritical marks from Quranic text
- Use verified text sources only — never manually type Quranic text
- Use Quranic fonts, not generic Arabic fonts
- Never log Quranic text in error/debug logs — use references (surah:ayah)
- Never use Quranic text as test data or placeholder text
- Label translations as translations, not as the Quran itself
- Never auto-play audio without user intent
What ships with it
19 files 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.
- references/adab.md 5.9 KB
- references/api-comparison.md 9.2 KB
- references/architecture.md 9.5 KB
- references/audio.md 7.3 KB
- references/content-types.md 4.8 KB
- references/data-models.md 8.2 KB
- references/data-sources.md 11 KB
- references/irab.md 5.8 KB
- references/memorization.md 7.3 KB
- references/mushaf-display.md 3.8 KB
- references/qiraat.md 9.8 KB
- references/quranpedia-api.md 11 KB
- references/quranpedia-embed.md 7.2 KB
- references/search.md 8.2 KB
- references/tajweed.md 5.9 KB
- references/testing-qa.md 7.7 KB
- references/text-rendering.md 7.0 KB
- references/translations-tafsir.md 5.1 KB
- references/verse-recognition.md 12 KB
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.
- 11d ago First seen · 104 lines · 264 tokens per session scan A 983486d2bea7
qurantech is a skill published in the GitHub repository quranpedia/qurantech-skill (4 stars, last pushed 29d ago), licensed MIT. It adds 264 tokens to every session and 1,921 once invoked, about $0.0013 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.