Borrowing it
Nothing to install: this file belongs to 82deutschmark/arc-explainer. 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/82deutschmark/arc-explainer/main/AGENTS.mdgit clone --depth 1 https://github.com/82deutschmark/arc-explainerWrote 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/82deutschmark/arc-explainer/agents-md)<a href="https://agentmods.dev/instructions/82deutschmark/arc-explainer/agents-md"><img src="https://agentmods.dev/badge/instructions/82deutschmark/arc-explainer/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/82deutschmark/arc-explainer/agents-md"><img src="https://agentmods.dev/badge/instructions/82deutschmark/arc-explainer/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 | $0.07434 | $0.07434 |
| Opus 5.5 | $0.02974 | $0.02974 |
| Sonnet 5.5 | $0.01487 | $0.01487 |
| Haiku 4.5 | $0.00743 | $0.00743 |
Grade A, and why
arc-explainer 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 5d 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 — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Author: The User (aka YOUR BOSS!!)
Date: 2025-12-31
Purpose: Guidance for AI agents working inside the ARC Explainer repository.
Table of Contents
- Mission & Critical Warnings
- Role, User Context & Communication
- Workflow, Planning & Version Control
- Coding Standards & File Conventions
- Documentation & Plan Index
- Repository Reference & Architecture
- Platform Expectations & Commands
- OpenAI Responses API & Streaming (CRITICAL)
- RE-ARC Benchmark System Overview
- ARC & RE-ARC Scoring
- SnakeBench / Worm Arena Notes
- Structured Outputs References
- Streaming Guide Snapshot
- Best Practices & Common Issues
- Prohibited Actions
ARC-3 game pages (18-Sep-2026): rebuilt level by level, and the same write-ups are served as JSON to the arc-3 training repo (
/api/arc3/dataset, token-gated). One level cut feeds the page, the JSON and/arc3/games.md:shared/arc3Games/gameLevels.ts. Before changing any of it readdocs/plans/2026-09-18-arc3-game-page-glowup-and-dataset-prd.md, Amendments first (Boss cut step budgets, code links and derived stats). Left:corrections[], and the public release only when Boss says so.
The ARC Daily Digest (reorganized 15-Oct-2026), for GPT-6.1 Sol, GPT-6 Luna, Claude and every newsroom run: start at
docs/newsroom/README.md, the map of every desk, schedule, folder and permission. Each desk then follows its own guide (REPORTER.md,WIRE_DESK.md,SOCIAL_DESK.md,X_POSTING.md,ART_DESK.md,FALLBACK.md). Standing rules live in those guides, one-off orders incontent/news/editorial-assignments.json(they expire), and each Codex job's short instruction indocs/newsroom/automation-prompts/. Head editor's completion order (22-Oct-2026): every newsroom assistant followsdocs/newsroom/FINISHING.md. A successful push ends publication; the editor saying they posted ends the send; one verification only; no deployment polling or work after completion. This overrides the older generic slow-down/ultrathink language below for newsroom work.
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.
- 5d ago Changed · +4 lines · +79 tokens per session 8c0263fda6b3
- 12d ago Changed · -2 lines · +22 tokens per session a978c0482ac0
- 14d ago Changed · +1 lines · +79 tokens per session 1bd7d464bf11
- 15d ago Changed · +36 lines · +767 tokens per session 91b82a12f42f
- 16d ago Changed · +4 tokens per session 2417aabce17d
- 17d ago Changed · +1 lines · +43 tokens per session fab3dcfcfc7e
- 18d ago Changed · +15 lines · +422 tokens per session 72249ccd9d89
- 1mo ago Changed · +7 lines · +152 tokens per session 0d9ce5d215c5
- 1mo ago First seen · 406 lines · 5,866 tokens per session scan A 34386456c7fa
arc-explainer AGENTS.md is an instructions file published in the GitHub repository 82deutschmark/arc-explainer (12 stars, last pushed today), licensed MIT. It adds 7,434 tokens to every session, about $0.0297 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.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.