skyrimvr-claude-toolkit: Instructions file for Codex

AGENTS.md

skyrimvr-claude-toolkit AGENTS.md is an instructions file for Codex, OpenCode from WingedGuardian/skyrimvr-claude-toolkit. It costs 7,581 tokens per session, scanned F, original, MIT.

Project instructions for AI coding agents working on a Skyrim VR modding toolkit. They explain which files and tools are shared across agents and which parts only work with Claude Code.

In plain words
What is it for?
Use them when configuring an agent for this Skyrim modding project, deciding what can be reused, or finding the correct instructions for tools, scripts, and engine differences.
Why use it?
They prevent agents from missing required project guidance or assuming that Claude Code-specific settings work elsewhere. They also point agents to the main instructions and technical reference.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is WingedGuardian/skyrimvr-claude-toolkit's own configuration. It tells Codex and OpenCode how to work on skyrimvr-claude-toolkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skyrimvr-claude-toolkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to WingedGuardian/skyrimvr-claude-toolkit. 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/WingedGuardian/skyrimvr-claude-toolkit/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/WingedGuardian/skyrimvr-claude-toolkit

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.

agentmods badge for skyrimvr-claude-toolkit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/wingedguardian/skyrimvr-claude-toolkit/agents-md/github.svg)](https://agentmods.dev/instructions/wingedguardian/skyrimvr-claude-toolkit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/wingedguardian/skyrimvr-claude-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/wingedguardian/skyrimvr-claude-toolkit/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.

agentmods 80×15 button for skyrimvr-claude-toolkit AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/wingedguardian/skyrimvr-claude-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/wingedguardian/skyrimvr-claude-toolkit/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,581 This file is loaded in full into every session.
When invoked 7,581 The same file — it is already loaded in full.
Security scan F 4 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07581 $0.07581
Opus 5.5 $0.03032 $0.03032
Sonnet 5.5 $0.01516 $0.01516
Haiku 4.5 $0.00758 $0.00758

Measured 2d ago against content hash 16bcc8829f18, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade F, and why

skyrimvr-claude-toolkit AGENTS.md scanned grade F with 4 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- GENERATED by scripts/gen_agent_trees.py from agent/instructions/core.md + codex.md. Toolkit contributors: edit the source. Your own notes belong in KNOWLEDGEBASE.local.md, which updates never replace. -->

Encoded or obfuscated payloadhighSupply chain

base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.

- Decoded text run as commands (`base64 -d | bash`), which the guard cannot read

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

that merely appear in a command (`grep -rn "rm -rf" <install>` is allowed). Relative paths resolve against

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- DevBench `smp reset` (measured to crash a large load order), by MCP, `curl` or `devbench-cli.sh`
AGENTS.md · 402 lines

How it starts

The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skyrim modding — agent instructions

Guidance for AI coding agents working in this Skyrim install. Agent-specific notes are at the end of this file.

What This Is

A modded Skyrim installation. Adapt paths and version-specific notes to your Skyrim version: SE, AE, VR, or LE. VR-specific behavior is flagged throughout — never assume SSE behavior equals VR behavior.

setup.sh detects your mod manager and fills in the Key Paths below accordingly. If it detected Mod Organizer 2, read the MO2 note in Key Paths before reading or writing any mod file — MO2 has no real Data/ folder, so the obvious path is the wrong one. See "Mod Manager Layout" in KNOWLEDGEBASE.md.

Key Paths

  • Game root: {{GAME_ROOT}}/
  • User INI configs: {{CONFIG_DIR}}/ (Skyrim.ini, SkyrimVR.ini, SkyrimPrefs.ini)
  • Load order: {{LOADORDER_DIR}}/loadorder.txt and plugins.txt
  • SKSE plugins: Data/SKSE/Plugins/
  • Mod data: Data/ (ESPs, BSAs, meshes, textures, scripts) {{MOD_MANAGER_PATHS}}

Installed Modding Tools

All under tools/:

Tool Purpose Usage
Champollion Decompile Papyrus .pex → .psc tools/Champollion/Champollion.exe input.pex
Caprica Compile Papyrus .psc → .pex tools/Caprica/Caprica.exe from Data/Scripts/Source with a BARE filename and a second -i for the base-game sources: exact command in skill skyrim-context
XEditLib.dll Programmatic ESP/ESM reading via FFI Load with koffi in Node.js (skill xelib)
Spriggit ESP ↔ YAML/JSON conversion (.NET) spriggit serialize ...
AutoMod CLI NIF meshes, BSA archives, audio, MCM, ESP one-liners bash tools/automod-cli.sh <module> <command> --json
PyFFI NIF geometry edit — NiTriShape (LE-format) ONLY (any modern Python with setuptools) PyFFI / PyNifly below; skill skyrim-nif
PyNifly NIF read/write incl. BSTriShape (SSE) + animation/controller authoring (Python, prebuilt DLL) PyFFI / PyNifly below; skill skyrim-nif
ReSaver CLI Headless .ess save parse / query / cross-reference / clean bash tools/resaver-cli.sh <op> <save.ess> — op list and rules: skill skyrim-save (write ops are dry-run unless --apply, always a NEW file). Needs JDK 17+ + ReSaver's jar (see docs/installing-tools.md).
cosave-info READ-ONLY structural survey of an SKSE .skse co-save → JSON (which mods stashed co-save data + how much) bash tools/cosave-cli.sh <cosave.skse> (Python 3; the cosave sits next to its .ess)
skyrim-winner "Which plugin actually wins this record?" Loads the FULL active load order and asks xEdit. No index, no cache -- xEdit is the authority. bash tools/skyrim-winner.sh <winner|chain> <formid> [plugin] · ... conflicts <plugin> -- needs xeditlib; skill triage-and-conflicts
papyrus-triage Turns Papyrus.N.log into bucketed, attributed counts. Rows sum to the entry count; the not-shown row prints even at zero. python tools/papyrus-triage.py [logfile] [--top N] [--all] -- bundled, Python 3, no install
crash-triage Reduces CrashLogger dumps (~5.5k lines each) to ranked signatures and labels the ones your knowledgebase already ruled on. python tools/crash-triage.py [dir|file] [--frames N] [--all] -- bundled, Python 3, no install
DevBench LIVE in-game inspect / console / Papyrus / scenario via a localhost REST+MCP server — only while the game is actually running bash tools/devbench-cli.sh <alive|health|ping|state|inspect|exec|call|describe|notify|tool> — skill devbench

Read the full file on GitHub · 402 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 Changed · +4 lines · +35 tokens per session 16bcc8829f18
  2. 23d ago Changed · +3 lines · +78 tokens per session ed896b3509bf
  3. 26d ago Changed · +341 lines · +6,633 tokens per session scan A → F 2f7f347fa541
  4. 1mo ago Changed · +98 tokens per session 2c510d18fae6
  5. 2mo ago First seen · 54 lines · 737 tokens per session scan A 02a2283d9613

Subscribe to this mod's changes

skyrimvr-claude-toolkit AGENTS.md is an instructions file published in the GitHub repository WingedGuardian/skyrimvr-claude-toolkit (21 stars, last pushed yesterday), licensed MIT. It adds 7,581 tokens to every session, about $0.0303 per session on Opus 5.5. A static security scan graded it F with 4 findings (hidden instructions, encoded or obfuscated payload, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

skyrimvr-claude-toolkit AGENTS.md compared with instructions from other repositories

skyrimvr-claude-toolkit AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skyrimvr-claude-toolkit AGENTS.mdWingedGuardian/skyrimvr-claude-toolkitInstructions file21yesterdayMITF7,581Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode