agentmods.dev

skills AGENTS.md

A repository guide for creating skills for Space Engineers, a game where scripts and mods can automate or change in-game systems. It describes the required skill folders and files and sets rules for keeping detailed guidance organised.

In plain words
What is it for?
Use it when developing Space Engineers scripting, modding, or plugin skills, especially when adding files, organising references, or writing the required top-level skill documentation.
Why use it?
It tells contributors how this skill collection is structured and what each skill must contain. This helps users find the right instructions without loading unnecessary detail.

Instructions file for CodexOpenCode

10 10d ago A scan 197 tokens original MIT
View the source file CometWorks/skills
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/cometworks/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/CometWorks/skills

Made for: Codex, OpenCode.

Per session 197 This file is loaded in full into every session.
When invoked 197 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 $0.00197 $0.00197
Opus 5 $0.00098 $0.00098
Sonnet 5 $0.00039 $0.00039
Haiku 4.5 $0.00020 $0.00020

Measured yesterday against content hash c2788cd91bb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills 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 yesterday.

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 · 12 lines

What it actually says

You are an experienced developer of Space Engineers in-game scripts, mods, and plugins.

  • All skills are located in the skills folder.
  • Each skill has its own dedicated subfolder within skills.
  • Each skill folder contains a top-level SKILL.md file.
  • Additional files related to a skill may be present within its respective folder.

Your objective is not to use these skills, but to develop them so that others can utilize them for specific tasks.

CRITICAL: Use progressive disclosure techniques to introduce details gradually, providing information only as it is required for the task. It is essential to maintain a directory tree of descriptions and summaries across multiple files and levels. This leads the reader to detailed pages step-by-step and is vital for keeping the context focused. Use relative paths to refer to the files with more details down the tree.

Read and internalize the project README.md before performing any other actions.

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. yesterday First seen · 12 lines · 197 tokens per session scan A c2788cd91bb8

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository CometWorks/skills (10 stars, last pushed 10d ago), licensed MIT. It adds 197 tokens to every session, about $0.0010 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 2026-08-31.

Building agentsWriting and docsaiai-agentsai-codingai-coding-assistantai-skillsautomated-coding
Related

Other instructions, from other repositories

attractor-guided-engineering-template AGENTS.md

Instructions for entropy-cloud/attractor-guided-engineering-template, covering agents.md, project intent, dual-audience repo, in-tree tool and task routing.

entropy-cloud/attractor-guided-engineering-template · 2,830 tokens

akm AGENTS.md

Instructions for itlackey/akm, covering akm repo notes, workflow, architecture, tests and test-isolation harness.

itlackey/akm · 2,755 tokens

claude-code-plugins AGENTS.md

Instructions for DropFan/claude-code-plugins, covering claude code plugins collection, repository structure, plugin management, development guidelines and adding a self-developed plugin.

DropFan/claude-code-plugins · 794 tokens

skills AGENTS.md

AGENTS.md instructions for payloadcms/skills, covering payload skills repository, repository overview, creating a new skill, directory structure and naming conventions.

payloadcms/skills · 729 tokens

codeframe AGENTS.md

AGENTS.md instructions for frankbria/codeframe: The guidelines for this repo live in CLAUDE.md. Read that file.

frankbria/codeframe · 145 tokens

codingbuddy nestjs.instructions.md

Instructions for JeremyDev87/codingbuddy, covering nestjs mcp server code review, module structure, mcp protocol and dependency injection.

JeremyDev87/codingbuddy · 129 tokens