TimberbornMods AGENTS.md

Repository instructions for AI coding agents working on Timberborn mods, a game that supports community-made modifications. They explain which guidance files to read, how rules are prioritized, and how agent roles work.

In plain words
What is it for?
Use them before changing the repository to find the applicable instructions, engineering guidance, Timberborn domain knowledge, and role boundaries.
Why use it?
They reduce mistakes caused by agents missing project-specific rules or reading the wrong guidance. They also clarify what to do when the agent environment lacks the coordination tools described.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/ihsoft/timberbornmods/agents-md
Clone the repo
git clone --depth 1 https://github.com/ihsoft/TimberbornMods

Made for: Codex, OpenCode.

Per session 7,288 This file is loaded in full into every session.
When invoked 7,288 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.07288 $0.07288
Opus 5 $0.03644 $0.03644
Sonnet 5 $0.01458 $0.01458
Haiku 4.5 $0.00729 $0.00729

Measured 2d ago against content hash a71a073a3fbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TimberbornMods 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 2d 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 · 545 lines

How it starts

The opening of the file, as written. The whole thing — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Instructions

This repository contains Timberborn mods.

These rules are repository rules for any AI agent working here. Some coordination steps mention Codex thread tools; if another agent environment does not provide those tools, follow the same role boundaries manually and ask the user to forward messages or provide the target role contact.

Before making changes, read this file and the instruction files that apply to the current task. Follow them unless the user explicitly says otherwise.

How to choose instructions to read

Always start with this root AGENTS.md.

Then load the active baseline layers in this order:

  1. If .agents/enable-ada exists, read docs/agent-profiles/Ada-Personality-v2.md for optional communication style and personality. If the marker is absent, do not load that profile. Do not infer opt-in from the user's language.
  2. Always read docs/agent-profiles/Engineering-Professional-v3.md for general engineering reasoning.
  3. Always read docs/agent-knowledge/Timberborn-Domain-Knowledge-v1.md for Timberborn-specific domain knowledge.

These layers complement this AGENTS.md; they do not replace repository, role, safety, local, or task-specific rules. They remain subject to the rule priority below.

Files named Operational Knowledge provide task-specific methods, evidence maps, and decision aids. They are not baseline profiles or independent safety policy. Load them only when a routing-table condition applies, together with the relevant repository, role, and local rules.

After the baseline layers, read only the instruction files that apply to the current task. Do not load every document blindly.

Condition Read
Generating or modifying C# code docs/csharp-formatting-rules-for-ai-agents.md
Modifying Timberborn C# behavior, general mod integration, non-building gameplay data, or package metadata not covered by a more specific route docs/timberborn-modding-rules-for-ai-agents.md and docs/agent-knowledge/Timberborn-Repository-Validation-Operational-Knowledge-v1.md
Creating or modifying building blueprints, building TemplateCollections, block layouts, entrances, construction states, placement, or building colliders docs/agent-knowledge/Timberborn-Buildings-Operational-Knowledge-v1.md and docs/agent-knowledge/Timberborn-Repository-Validation-Operational-Knowledge-v1.md
Adding or modifying player-facing text, localization keys or files, localized UI strings, or ILoc usage docs/agent-knowledge/Timberborn-Localization-Operational-Knowledge-v1.md and docs/agent-knowledge/Timberborn-Repository-Validation-Operational-Knowledge-v1.md
Creating or modifying player-facing game icons or loose PNG/JPG sprite assets docs/agent-knowledge/Timberborn-Icon-Operational-Knowledge-v1.md and docs/agent-knowledge/Timberborn-Repository-Validation-Operational-Knowledge-v1.md
Creating or modifying Steam Workshop, Mod.IO, or GitHub thumbnails, previews, slideshow images, promotional screenshots, or banners docs/agent-knowledge/Timberborn-Promotional-Visual-Operational-Knowledge-v1.md
Modifying Workshop indexing or search tools, scheduled or backfill workflows, gallery or visual classification, published search schema or Pages artifacts, or a frontend or in-game consumer of the public index docs/agent-knowledge/Timberborn-Workshop-Search-Index-Operational-Knowledge-v1.md
Working with ModsUnityProject, Unity-owned package data, compatibility lanes, or Unity export docs/agent-knowledge/Timberborn-Unity-Operational-Knowledge-v1.md and docs/agent-knowledge/Timberborn-Repository-Validation-Operational-Knowledge-v1.md
Changing Timberborn game, Unity Editor, or Unity package versions; running the importer; refreshing or validating imported game assemblies docs/agent-knowledge/Timberborn-Unity-Import-Operational-Knowledge-v1.md and docs/agent-knowledge/Timberborn-Unity-Operational-Knowledge-v1.md
Starting any agent-controlled Unity Editor or batch-mode launch for this repository's work, including a separate project, or staging, creating, or verifying a Git commit docs/agent-knowledge/Repository-Coordination-Operational-Knowledge-v2.md
Creating or modifying in-game UI Toolkit views, UXML, USS, dialogs, panels, or fragments docs/timberborn-ui-toolkit-notes-for-ai-agents.md and docs/agent-knowledge/Timberborn-Repository-Validation-Operational-Knowledge-v1.md
Locating, extracting, generating, modifying, or packaging Timberborn .timbermesh models docs/agent-knowledge/Timberborn-Timbermesh-Operational-Knowledge-v1.md
Modifying instantiated runtime UnityEngine.Mesh geometry, UVs, or per-entity visualization meshes docs/agent-knowledge/Timberborn-Runtime-Unity-Mesh-Operational-Knowledge-v1.md
Designing, creating, porting, reviving, or integrating a Timberborn mod project docs/agent-knowledge/Timberborn-New-Mod-Operational-Knowledge-v1.md
Backporting mod features or fixes to an older Timberborn game line docs/agent-knowledge/Timberborn-Backport-Operational-Knowledge-v1.md and docs/agent-knowledge/Timberborn-Repository-Validation-Operational-Knowledge-v1.md
Designing a new feature inside an existing mod docs/timberborn-modding-howto-for-ai-agents.md, docs/timberborn-repository-notes.md, and docs/timberborn-lessons-learned.md
Investigating architecture or implementation approach docs/timberborn-repository-notes.md and docs/timberborn-lessons-learned.md
Diagnosing build, export, mod loading, runtime, UI, save/load, or platform behavior docs/agent-knowledge/Timberborn-Diagnostics-Operational-Knowledge-v1.md
Editing or reviewing GitHub Wiki pages docs/agent-knowledge/Wiki-Operational-Knowledge-v1.md and docs/timberborn-wiki-editing-rules-for-ai-agents.md
Working with TimberCommons docs/TimberCommons-modding-notes-for-ai-agents.md
Bootstrapping a copied or new repository docs/timberborn-new-repository-bootstrap-for-ai-agents.md
Preparing, validating, packaging, or publishing a release docs/timberborn-release-publishing-rules-for-ai-agents.md
Organizing or updating agent rules This AGENTS.md, docs/agent-knowledge/Mentor-Rule-Maintenance-Operational-Knowledge-v1.md, relevant files under docs/, and any local AGENTS.md whose scope is being changed

Read the full file on GitHub · 545 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.

  1. 2d ago First seen · 545 lines · 7,288 tokens per session scan A a71a073a3fbd

Subscribe to this mod's changes

TimberbornMods AGENTS.md is an instructions file published in the GitHub repository ihsoft/TimberbornMods (11 stars, last pushed 7d ago), licensed Unlicense. It adds 7,288 tokens to every session, about $0.0364 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.

Related

Other instructions, from other repositories