What is tilawa AGENTS.md?

Project instructions for Tilawa, an offline Quran verse-recognition software development kit. It accepts 16 kHz audio and identifies the matching surah and verse on the device, without sending audio to a server.

Use them when developing the TypeScript SDK, browser demo, audio recognition pipeline, verse matching, streaming tracking, or related tests.

They explain which code is shipped, how recognition works, and how research code relates to the SDK, reducing mistakes when changing the project.

How yazinsai/tilawa configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to yazinsai/tilawa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/yazinsai/tilawa/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/yazinsai/tilawa

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/yazinsai/tilawa/agents-md/github.svg)](https://agentmods.dev/instructions/yazinsai/tilawa/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/yazinsai/tilawa/agents-md"><img src="https://agentmods.dev/badge/instructions/yazinsai/tilawa/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/yazinsai/tilawa/agents-md"><img src="https://agentmods.dev/badge/instructions/yazinsai/tilawa/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,849 This file is loaded in full into every session.

When invoked 1,849 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01849	$0.01849
Opus 5.5	$0.00740	$0.00740
Sonnet 5.5	$0.00370	$0.00370
Haiku 4.5	$0.00185	$0.00185

Measured 1mo ago against content hash 81fcb9ad4144, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tilawa AGENTS.md 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 1mo 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.

AGENTS.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tilawa

Offline Quran verse recognition — give it 16kHz audio, get surah:ayah. Fully on-device (web / node / React Native).

This repo ships two things:

@tilawa/core (packages/core/) — the SDK. Pure TypeScript, zero native deps. Default engine: streaming Zipformer2-CTC over tajweed phonemes (src/recitation/). Alternate engine: FastConformer text CTC. The app dev passes in their onnxruntime build; the SDK never imports it.
Web demo (web/) — live browser recitation demo that consumes @tilawa/core as its regression guard.

The Python research/training/benchmark harness lives under lab/ and has its own lab/AGENTS.md. Model weights are proven out there, then their logic graduates into the SDK.

Layout

packages/core/     # @tilawa/core SDK (the shipped product)
  src/
    index.ts             # createRecognitionSession (engine switch), createTilawaSession, TilawaAssets
    recitation/          # default Zipformer engine
      session.ts         #   ZipformerSession / createZipformerSession — {ort, model} or {session, Tensor}
      zipformerRunner.ts #   ONNX I/O over the injected ort namespace
      fbank.ts, ctcDecoder.ts, search.ts, tracker.ts, engine.ts, emission.ts, correction.ts, ...
      zipformer-io.json  #   bundled I/O manifest (DEFAULT_ZIPFORMER_IO)
    session.ts           # SessionRunner seam — FastConformer only (type-only, no onnxruntime)
    quran-db.ts          # QuranDB — display text + FastConformer verse matching
    tracker.ts, text-ctc-decode.ts, quran-text-adapter.ts, ctc-rescore.ts  # FastConformer pipeline
    levenshtein.ts, normalizer.ts, types.ts  # shared helpers + WorkerOutbound event union
  test/                  # deterministic vitest (no ONNX)
  examples/
    browser/index.html   # no-bundler page: import map -> dist + onnxruntime-web, file + mic input
    browser/test.mjs     # headless Chromium regression over test_corpus (npm run test:browser)
    session-*.ts, react-native.md  # copy-paste runtime adapters
web/                     # live browser demo (Vite + worker), consumes @tilawa/core src
  frontend/src/worker/zipformer-backend.ts  # the web Zipformer host (onnxruntime-web)
  frontend/scripts/fetch-zipformer-assets.sh  # model + corpus -> public/ (gitignored, NPL-1.2)
lab/                     # Python research/training/benchmark harness — see lab/AGENTS.md
.github/workflows/ci.yml # core (vitest), browser (test:browser), demo (build)
README.md, Dockerfile, LICENSE

Read the full file on GitHub · 121 lines

Changes

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.

1mo ago Changed · +11 lines · +560 tokens per session 81fcb9ad4144
1mo ago Changed · +8 tokens per session fd6228888f42
2mo ago First seen · 110 lines · 1,281 tokens per session scan A 71b27c869810

Subscribe to this mod's changes

tilawa AGENTS.md is an instructions file published in the GitHub repository yazinsai/tilawa (347 stars, last pushed 1mo ago), licensed MIT. It adds 1,849 tokens to every session, about $0.0074 per session on Opus 5.5. 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 2026-08-30.

Languages Rust Scientific

tilawa AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tilawa AGENTS.mdyazinsai/tilawa	Instructions file	347	1mo ago	MIT	A	1,849	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

tilawa: Instructions file for Codex