What is ai-repo-adventures AGENTS.md?

Repository instructions for a project that builds AI-generated adventure content and runs an MCP server using TypeScript packages.

Running the server, watching files during development, generating HTML or other content formats, linting code, and running unit, integration, or system tests.

They collect the commands for building, developing, checking, testing, and cleaning up generated content.

How DanWahlin/ai-repo-adventures configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to DanWahlin/ai-repo-adventures. 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/DanWahlin/ai-repo-adventures/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/DanWahlin/ai-repo-adventures

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/danwahlin/ai-repo-adventures/agents-md/github.svg)](https://agentmods.dev/instructions/danwahlin/ai-repo-adventures/agents-md)

Your own site

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

Per session 3,282 This file is loaded in full into every session.

When invoked 3,282 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	$0.03282	$0.03282
Opus 5.5	$0.01313	$0.01313
Sonnet 5.5	$0.00656	$0.00656
Haiku 4.5	$0.00328	$0.00328

Measured 2mo ago against content hash 0d8f2ad9ddf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-repo-adventures 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 · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

IMPORTANT: As Claude runs tests that generate content, always clean up the content once done if it's temporary and not needed for the project.

Development Commands

Build: npm run build - Compiles all TypeScript packages using workspace dependencies
Run: npm start - Runs the production MCP server
Development: npm run dev - Runs with file watching for development
Adventure Generation: npm run generate-html - Interactive CLI for creating themed adventure content in multiple formats (HTML, Markdown, JSON, XML, Text)

Linting Commands

Lint All: npm run lint - Check code quality and complexity
Lint Fix: npm run lint:fix - Auto-fix linting issues where possible
Complexity Check: npm run lint:complexity - Focus on cyclomatic complexity analysis

Testing Commands

All Tests: npm test - Runs comprehensive test suite across all packages
Unit Tests: npm run test:unit - Core algorithm and component tests
Integration Tests: npm run test:integration - LLM provider and repomix integration tests
System Tests:
- npm run test:simple - Basic MCP workflow validation (2 minutes timeout)
- npm run test:real-world - Full system integration with performance monitoring
- npm run chat - Interactive terminal-based testing client
Content Generation Tests:
- npm run test:html - Quick HTML generation (minimal LLM calls for fast testing)
- npm run test:md - Quick Markdown generation for testing format strategies
- npm run test:prompts - LLM prompt analysis and debugging

LLM Configuration (Optional)

The system works without LLM configuration (using fallback templates), but LLM enables dynamic story generation:

cp .env.example .env
# Configure LLM_API_KEY, LLM_BASE_URL, LLM_MODEL

Code Review Policy

ALWAYS use the code-reviewer agent after writing or significantly modifying code. This includes:

New files or components
Major refactoring or architectural changes
Bug fixes that affect multiple functions
Feature additions or enhancements
Performance optimizations
Security-related changes

Read the full file on GitHub · 295 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 · 295 lines · 3,282 tokens per session scan A 0d8f2ad9ddf2

Subscribe to this mod's changes

ai-repo-adventures AGENTS.md is an instructions file published in the GitHub repository DanWahlin/ai-repo-adventures (8 stars, last pushed 3mo ago), licensed MIT. It adds 3,282 tokens to every session, about $0.0131 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.

ai mcp repos

ai-repo-adventures AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-repo-adventures AGENTS.mdDanWahlin/ai-repo-adventures	Instructions file	8	3mo ago	MIT	A	3,282	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
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ai-repo-adventures: Instructions file for Codex