Borrowing it
Nothing to install: this file belongs to bcorfman/arcadeactions. 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/bcorfman/arcadeactions/main/AGENTS.mdgit clone --depth 1 https://github.com/bcorfman/arcadeactionsWrote 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/bcorfman/arcadeactions/agents-md)<a href="https://agentmods.dev/instructions/bcorfman/arcadeactions/agents-md"><img src="https://agentmods.dev/badge/instructions/bcorfman/arcadeactions/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/bcorfman/arcadeactions/agents-md"><img src="https://agentmods.dev/badge/instructions/bcorfman/arcadeactions/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 | $0.00335 | $0.00335 |
| Opus 5.5 | $0.00134 | $0.00134 |
| Sonnet 5.5 | $0.00067 | $0.00067 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
arcadeactions 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 1mo 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.
What it actually says
Read before coding:
- Follow docs in order:
docs/prd.md->docs/api_usage_guide.md->docs/testing_guide.md. - Refer to
/docsfor any context or patterns before implementation.
Design priorities (in order): dev experience, simplicity, fit with underlying APIs, API quality, testability, best practices.
Structure/complexity:
- Keep modules around ~500 lines and functions around ~20 cyclomatic complexity.
- Split modules/functions intelligently to avoid high complexity or large files.
- If splitting would reduce clarity, ask for a decision before doing it.
Hard rules:
- Avoid dataclasses unless there is a clear, documented benefit.
- Avoid runtime type/attribute checks (hasattr/getattr/isinstance/EAFP-with-pass).
- No silent EAFP;
except AttributeError: passis forbidden. - Use
uv run python(never plainpython). - Define and use explicit Protocols/adapters for sprite/window/action interfaces; validate at boundaries instead of ad-hoc attribute probes.
Dependency/testability:
- Accept dependencies via constructors; avoid hidden instantiation inside methods.
- Avoid circular dependencies.
- Prefer composition over inheritance for dependencies.
E2E verification (required when fixing failures):
- When addressing an E2E failure (local or CI), re-run E2E locally for the browser/project(s) that failed (e.g. Playwright
--project=<name>/PW_PROJECT=<name>), not just a default browser. - If you can’t run the failing browser(s) locally, explicitly state why and run the closest equivalent verification (and call out the remaining risk).
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.
- 1mo ago Changed · +4 lines · +93 tokens per session 8bdee0bbc915
- 2mo ago First seen · 23 lines · 242 tokens per session scan A 6fd2b4bd7017
arcadeactions AGENTS.md is an instructions file published in the GitHub repository bcorfman/arcadeactions (5 stars, last pushed 7d ago), licensed MIT. It adds 335 tokens to every session, about $0.0013 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.
arcadeactions AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| arcadeactions AGENTS.mdbcorfman/arcadeactions | Instructions file | 5 | 7d ago | MIT | A | 335 | 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 | yesterday | 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 ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |