What is CyberCba2077 AGENTS.md?

Repository-specific instructions for coding agents working on the CyberCba2077 game project.

Use them when changing that repository so the agent reads the relevant specifications, follows the current C++ style rules, and checks existing code and tests.

They tell an agent which documents describe the game, architecture, coding rules, dependencies, and required gameplay, reducing the chance of changes that conflict with the project.

How GabrielEValenzuela/CyberCba2077 configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to GabrielEValenzuela/CyberCba2077. 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/GabrielEValenzuela/CyberCba2077/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/GabrielEValenzuela/CyberCba2077

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gabrielevalenzuela/cybercba2077/agents-md/github.svg)](https://agentmods.dev/instructions/gabrielevalenzuela/cybercba2077/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/gabrielevalenzuela/cybercba2077/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrielevalenzuela/cybercba2077/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/gabrielevalenzuela/cybercba2077/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrielevalenzuela/cybercba2077/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,018 This file is loaded in full into every session.

When invoked 1,018 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.

Model	Per session	Once invoked
Fable 5.1	$0.01018	$0.01018
Opus 5.5	$0.00407	$0.00407
Sonnet 5.5	$0.00204	$0.00204
Haiku 4.5	$0.00102	$0.00102

Measured 2mo ago against content hash 67bf7ce9cdc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

CyberCba2077 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for any coding agent (Claude Code, Codex, Cursor, etc.) working in this repository. Kept short on purpose — full context lives in the docs below; read only what the current task needs instead of the whole tree.

Read in this order, only as deep as the task requires

docs/GPD.md — product/narrative/gameplay truth. Read when the task touches what the game does.
docs/TAD-001.md — architecture/engineering rules. Read when the task touches how code is structured. Sections 22-25 (naming/format) are superseded — see ADR-001 below instead.
docs/adr/ADR-001-cpp-style-guide-merge.md — the actual naming/format rules in force (m_ members, #ifndef guards, Allman braces, 120 cols).
docs/adr/ADR-002-vcpkg-dependency-management.md — dependency versions and vcpkg setup (supersedes TAD-001 §35's version numbers).
docs/specs/VS-001.md — the Vertical Slice spec (Prologue + Mission 1): exact scenes, puzzle/combat numbers, required classes. Read when implementing or changing gameplay content/logic.
Existing code + tests — the actual current state. Trust this over any doc summary (including this file) if they disagree; then fix the doc.

Don't re-read a doc you've already loaded this session just to double-check phrasing. These docs don't change mid-task.

Hard constraints (violating these is not a style choice, it fails CI)

No STL containers (std::vector, std::map, std::queue, std::stack, std::set, etc.) and no std::unique_ptr/std::shared_ptr anywhere in include//src/. Enforced by CI's forbidden-symbols-audit job (a grep, not a suggestion). std::string/std::string_view are fine.
cybercba_core MUST NOT #include <raylib.h> or call any raylib function. Gameplay logic must be testable without a window.
The four ADTs in include/cybercba/structures/ (DynamicArray, Queue, Stack, DirectedGraph) are headers-only by design — a student exercise, not an oversight. Do not implement their bodies unless explicitly asked to. PuzzleSystem compiles against them but is isolated in the cybercba_core_puzzle object-library target precisely so the rest of the tree keeps linking while they're unimplemented.
.clang-format/.clang-tidy are the actual style contract — run clang-format -i on touched files before considering a change done, don't hand-format.

Read the full file on GitHub · 78 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.

2mo ago First seen · 78 lines · 1,018 tokens per session scan A 67bf7ce9cdc8

Subscribe to this mod's changes

CyberCba2077 AGENTS.md is an instructions file published in the GitHub repository GabrielEValenzuela/CyberCba2077 (10 stars, last pushed 2mo ago), licensed MIT. It adds 1,018 tokens to every session, about $0.0041 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.

Game development

CyberCba2077 AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
CyberCba2077 AGENTS.mdGabrielEValenzuela/CyberCba2077	Instructions file	10	2mo ago	MIT	A	1,018	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	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	yesterday	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	1,907	GitHub Copilot

CyberCba2077: Instructions file for Codex