prep-jee: Instructions file for Codex

AGENTS.md

prep-jee AGENTS.md is an instructions file for Codex, OpenCode from DuskyElf/prep-jee. It costs 9,134 tokens per session, scanned A, original, Unlicense.

A project instruction file that documents how a browser-based JEE practice app works. JEE is an Indian engineering entrance exam.

In plain words
What is it for?
It guides work on PDF uploads, question and answer extraction, interactive quizzes, grading, and browser-only deployment.
Why use it?
It gives coding agents one place to find the project’s workflow, constraints, and implementation details.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is DuskyElf/prep-jee's own configuration. It tells Codex and OpenCode how to work on prep-jee itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything prep-jee configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DuskyElf/prep-jee. 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/DuskyElf/prep-jee/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/DuskyElf/prep-jee

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.

agentmods badge for prep-jee AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/duskyelf/prep-jee/agents-md/github.svg)](https://agentmods.dev/instructions/duskyelf/prep-jee/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/duskyelf/prep-jee/agents-md"><img src="https://agentmods.dev/badge/instructions/duskyelf/prep-jee/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.

agentmods 80×15 button for prep-jee AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/duskyelf/prep-jee/agents-md"><img src="https://agentmods.dev/badge/instructions/duskyelf/prep-jee/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,134 This file is loaded in full into every session.
When invoked 9,134 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.09134 $0.09134
Opus 5.5 $0.03654 $0.03654
Sonnet 5.5 $0.01827 $0.01827
Haiku 4.5 $0.00913 $0.00913

Measured 2mo ago against content hash 6a36bec9578c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prep-jee 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 2mo 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 · 654 lines

How it starts

The opening of the file, as written. The whole thing — 654 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the single source of project wisdom. Make sure to keep this up to date with the project.


What this is

Client-side web app: upload a JEE Test PDF + Solution PDF → extracts questions & answer key → interactive quiz → grading with solution pages.

Target user: JEE (Joint Entrance Exam) aspirants practicing with weekly test PDFs from coaching institutes (e.g., PW Arjuna, Allen, Aakash). The app runs entirely in the browser — no server, no uploads to external services.

Constraints: Fully client-side. pdf.js from npm (pdfjs-dist) bundled via Vite. PDF text extraction via getTextContent() — no OCR. Deployed to Cloudflare Pages.


Core workflow

  1. Upload — Two separate drop zones (Test PDF / Solution PDF). User explicitly picks which is which. No auto-detection.
  2. Parse — pdf.js getTextContent() → reconstructLines() (content-stream order, no y-sort) → text → parsers.
  3. Quiz — One question at a time. Controls adapt to type (radio/checkbox/text input). Navigator popup (🔍 Jump button or / key) for jumping between questions. State managed by SolidJS createStore in store.ts.
  4. Results — Score with per-question breakdown. Linked solution pages from the solution PDF. Resume banner on reload via localStorage.

Entry point: src/index.tsx renders <App /> into <div id="root">. All screens routed via <Show when={state.screen === '...'}> within App.tsx — no router library.


Features (all ✅ done)

  • Quiz countdown timer — Duration parsed from the test PDF's first page (looks for DURATION : 180 Minutes pattern). Uses absolute timestamp (startedAt) stored in localStorage, so the timer survives page refreshes. Auto-submits when time runs out. Warning color at <5 min, critical at <1 min. Displayed on both quiz and results screens.
  • Two upload sections — Two explicit drop zones, each with its own file input. Validation compares questions.length vs Object.keys(answers).length, throws error with exact counts on mismatch.
  • 2D page cropping — Each question shows only its portion of the PDF page, cropped on both x and y. reconstructLines() tracks { minY, maxY, minX, maxX } per line. Falls back: no bbox → full page, no x-bounds → y-only crop.
  • Multi-column span notice — Amber notice when a question's x-range covers >55% of the page content width (text in one column, options in another).
  • Question navigator — Pop-up grid via "🔍 Jump" button or / key. Green border = answered, purple+glow = current. 1-9 jumps, Escape closes.
  • Resume from localStorage — userAnswers + currentQ saved per PDF filename pair. Validates saved qnums match current question set on reload.
  • Debug panel — Raw extracted text for first 3 pages. Console debug dump with full question/answer/userAnswer/solutionPageMap data.

Read the full file on GitHub · 654 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.

  1. 2mo ago First seen · 654 lines · 9,134 tokens per session scan A 6a36bec9578c

Subscribe to this mod's changes

prep-jee AGENTS.md is an instructions file published in the GitHub repository DuskyElf/prep-jee (5 stars, last pushed 3mo ago), licensed Unlicense. It adds 9,134 tokens to every session, about $0.0365 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 2026-08-31.

Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,461 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens