Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/theredbluepill/arc-interactive/agents-mdgit clone --depth 1 https://github.com/theredbluepill/arc-interactiveWhat 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 | $0.05009 | $0.05009 |
| Opus 5 | $0.02505 | $0.02505 |
| Sonnet 5 | $0.01002 | $0.01002 |
| Haiku 4.5 | $0.00501 | $0.00501 |
Grade A, and why
arc-interactive 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 3d 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 — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARCAGI-3 Game Designer Agent
Role
Agent responsible for designing and implementing ARC-AGI-3 games.
Benchmark principle
ARC-AGI-style benchmarks are about whether an AI can solve puzzles that humans can solve when both operate under the same official interface: defined actions, observation format, and stated game rules. The goal is to measure general problem-solving, not which system had the most task-specific training data or memorized solutions.
When you author games in this repo, treat human solvability (given that shared spec) as a design guide: prefer well-posed levels—where goals are clear from layout, mechanics, or fair in-observation cues—over under-specified puzzles that only yield to guessing, huge search, or spoilers absent from the agent’s observation.
Workflow
1. Game Design Phase
Input: Game concept or requirements Output: Game specification
Key Questions:
- Grid size? (8x8, 16x16, 24x24, 64x64)
- What entities? (player, targets, walls, hazards)
- What actions? (define what ACTION1-7 mean for your game)
- Win/lose conditions?
2. Implementation Phase
Input: Game specification
Output: Working game in environment_files/
Steps:
- Create directory:
environment_files/{stem}/{version}/(two-letter stem + digits, e.g.ez01; version folder is usuallyv1on first landing, then often an 8-char git prefix after CI — seeCONTRIBUTING.md) - Implement
{stem}.pywith:- Sprite definitions
- Static levels (no PCG)
- Game class extending
ARCBaseGame - Win/lose conditions
- Test with:
arc.makeusing the fullgame_idfrom that folder’smetadata.json, or locallyuv run python run_game.py --game {stem} --version auto— add--mode humanfor pygame hand-play (scripts/human_play_pygame.py).
3. Documentation Phase
Input: Completed game Output: Updated tracking files
Steps:
- Add entry to
GAMES.mdwith all metadata columns - If you discover a reusable pattern (not stem-specific), add a short bullet under Lessons learned (cross-repo) below; otherwise rely on
GAMES.md,{stem}.py, andscripts/render_arc_game_gif.py(see skillgenerate-arc-game-gifinskills/) - Optional: add
assets/{stem}.gifusing the generate-arc-game-gif skill (advancing levels + 1–2 fail clips, HUD inRenderableUserDisplay)
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.
- 3d ago First seen · 467 lines · 5,009 tokens per session scan A 9e15177911f6
arc-interactive AGENTS.md is an instructions file published in the GitHub repository theredbluepill/arc-interactive (54 stars, last pushed 2mo ago), licensed MIT. It adds 5,009 tokens to every session, about $0.0250 per session on Opus 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.
Other instructions, from other repositories
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
unity-cli-skill CLAUDE.md
Instructions for niqibiao/unity-cli-skill: Project instructions are maintained in and imported from @AGENTS.md.
Nyamu AGENTS.md
Instructions for polyblank66/Nyamu, covering about mcp, nyamu mcp workflow guidelines, file operation workflows, compilation tools and error handling.
sts2-llm copilot-instructions.md
Instructions for ttxttx1111/sts2-llm, covering copilot instructions for this repository, source of truth for customizations, runtime assumptions, authoring rules for this repo and gameplay-specific expectations.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.