Borrowing it
Nothing to install: this file belongs to abdshomad/ocr-arena. 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/abdshomad/ocr-arena/main/AGENTS.mdgit clone --depth 1 https://github.com/abdshomad/ocr-arenaWrote 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/abdshomad/ocr-arena/agents-md)<a href="https://agentmods.dev/instructions/abdshomad/ocr-arena/agents-md"><img src="https://agentmods.dev/badge/instructions/abdshomad/ocr-arena/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/abdshomad/ocr-arena/agents-md"><img src="https://agentmods.dev/badge/instructions/abdshomad/ocr-arena/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 | $0.00786 | $0.00786 |
| Opus 5.5 | $0.00314 | $0.00314 |
| Sonnet 5.5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
ocr-arena 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines: OCR Arena
This repository implements the OCR Arena web application. AI agents working in this repository must adopt and follow the guidelines defined in the andrej-karpathy-skills submodule.
1. Core Behavioral Guidelines
Adhere strictly to CLAUDE.md:
- Think Before Coding: Avoid assumptions. Ask the user if there's any ambiguity.
- Simplicity First: Implement only requested features without speculative abstractions.
- Surgical Changes: Touch only what is required. Match the existing codebase style.
- Goal-Driven: Define success criteria first and systematically verify changes.
2. Web Stack & Paths
- Frontend: Next.js (App Router, Tailwind CSS, TypeScript).
- Database: PostgreSQL (initialized automatically on demand).
- Backend APIs: Served via Docker under
ocr-enginesconfiguration.- Layout parsing APIs on ports
8090-8093. - vLLM servers on ports
8118-8121.
- Layout parsing APIs on ports
- Relative Paths Only: Never use absolute paths containing username (e.g.
/home/user/path). Use relative paths (e.g.,.or./path).
3. App Testing & Screenshots
- E2E tests are run only when explicitly requested (using "test" or "t").
- Execute tests via:
uv venv && source .venv/bin/activate && uv sync && uv run playwright install uv run python3 -m tests.run_all - Save step-by-step screenshots to
/screenshots/using the format:{NN}-{step}-{variant_if_any}-{slug}.jpg(e.g.,01-step1-default-upload.jpg).
4. Issue Recording
Record any installation, server, debugging, or client integration issue in issues/ immediately as issues/{NN}-{slug}.md using the following format:
# Issue {NN}: {Short title}
## Problem
What failed, with exact error or symptom.
## Context
Environment, command run, and relevant config.
## Solution
What fixed it or current status/workaround.
5. Autonomous Enhancements Plan
When requested, manage enhancements in plan/next-enhancements.md:
- "enhance" / "e": Plan at least 3 pending enhancements (
[TODO]) for each section (Compare Workspace, Scan History, Telemetry & Analytics). Report the plan to the user. - "next" / "n": Locate the active task list, execute the next pending task, update its status to
[DONE]in bothAGENTS.mdand the plan, and stop.
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.
- 2mo ago First seen · 71 lines · 786 tokens per session scan A 5fa41ae23b8f
ocr-arena AGENTS.md is an instructions file published in the GitHub repository abdshomad/ocr-arena (2 stars, last pushed 5mo ago), licensed MIT. It adds 786 tokens to every session, about $0.0031 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.
ocr-arena AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ocr-arena AGENTS.mdabdshomad/ocr-arena | Instructions file | 2 | 5mo ago | MIT | A | 786 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |