Borrowing it
Nothing to install: this file belongs to yukuku/androidbible. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yukuku/androidbible/develop/AGENTS.mdgit clone --depth 1 https://github.com/yukuku/androidbibleWrote 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/instructions/yukuku/androidbible/agents-md)<a href="https://agentmods.dev/instructions/yukuku/androidbible/agents-md"><img src="https://agentmods.dev/badge/instructions/yukuku/androidbible/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.
<a href="https://agentmods.dev/instructions/yukuku/androidbible/agents-md"><img src="https://agentmods.dev/badge/instructions/yukuku/androidbible/agents-md.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 | $0.03904 | $0.03904 |
| Opus 5.5 | $0.01562 | $0.01562 |
| Sonnet 5.5 | $0.00781 | $0.00781 |
| Haiku 4.5 | $0.00390 | $0.00390 |
Grade A, and why
androidbible AGENTS.md 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 today.
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.
- **Backend host:** `BuildConfig.SERVER_HOST` resolves to `https://api.alkitab.app` (defined in `Alkitab/build.gradle.kts`), **not** the marketing site at `alkitab.app`. The two hostnames are different origins behind sep How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
Project Overview
Bible for Android (Alkitab / Quick Bible) — a 100% free, open-source Bible reader app for Android. Published on Google Play as "Alkitab" (Indonesian) and "Quick Bible" (non-Indonesian). The codebase supports multiple product flavors, 100+ downloadable Bible versions, song books, devotions, reading plans, cloud sync, and a daily verse widget.
- Official site: https://alkitab.app
- Developer docs: https://alkitab.app/developer
Branches
develop is the main integration branch. Base all work on develop and target every PR at develop. Use short-lived release branches when needed and tags to identify beta and production releases. The retired master branch is preserved by the archive/master tag.
Task completion and communication
Explain agent-made choices in the final response
At the end of a task, explain the consequential choices you made that the user did not explicitly specify. Do this by default, without waiting for the user to ask. Distinguish the user’s requirements from your assumptions and decisions, and briefly explain why you chose them and what they mean for the resulting behavior.
Focus on choices the user would reasonably want to review, such as how you interpreted loose requirements, UI placement and interactions, defaults, persistence, scope, and tradeoffs. Scale the detail to the ambiguity and impact of the task. Do not bury these choices in a list of changed files or a chronological work log, and do not enumerate routine implementation details. If there were no consequential choices beyond the request, do not invent any.
Include the outcome, relevant validation, and remaining limitations alongside these decisions. This reporting requirement does not create an additional approval step for work already authorized.
Task context and pull requests
When the agent runs in a cloud environment or the user assigns a task in a dedicated Git worktree, finish the task by committing the changes, pushing its task branch to yukuku/androidbible, and creating or updating a pull request targeting develop, unless the user explicitly requests otherwise. The cloud-environment requirement applies even when the checkout is not a dedicated worktree. Creating or updating the PR is part of completing the task; do not ask for separate permission.
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.
- today Changed · +2 lines · +99 tokens per session 23c30825ddd6
- 8d ago Changed · +8 lines · +140 tokens per session 0412ca0f8ce9
- 9d ago Changed · -141 lines · -2,507 tokens per session ed1c7963ce7a
- 10d ago Changed · +13 lines · +270 tokens per session 7b01b601369a
- 14d ago Changed · -1 lines · -29 tokens per session 22fa272d400f
- 15d ago Changed · -64 lines · -1,121 tokens per session e6e768c73428
- 16d ago Changed · +3 lines · +254 tokens per session f272771823c0
- 23d ago Changed · +13 lines · +202 tokens per session 6359860c4fa1
- 27d ago First seen · 323 lines · 6,596 tokens per session scan A cdacca6294be
androidbible AGENTS.md is an instructions file published in the GitHub repository yukuku/androidbible (366 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,904 tokens to every session, about $0.0156 per session on Opus 5.5. 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 2026-10-03.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.