What is skills AGENTS.md?

Instructions for developing and maintaining AI-agent skills in a source repository. They explain where the editable source files live and distinguish them from installed copies.

Adding or updating skills, following the repository layout, committing changes, and reinstalling skills from their source repository.

They prevent changes from being made to installed files that would later be overwritten or fail to reach other machines.

How Randroids-Dojo/skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Randroids-Dojo/skills. 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/Randroids-Dojo/skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Randroids-Dojo/skills

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/randroids-dojo/skills/agents-md/github.svg)](https://agentmods.dev/instructions/randroids-dojo/skills/agents-md)

Your own site

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

Per session 1,024 This file is loaded in full into every session.

When invoked 1,024 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	$0.01024	$0.01024
Opus 5.5	$0.00410	$0.00410
Sonnet 5.5	$0.00205	$0.00205
Haiku 4.5	$0.00102	$0.00102

Measured 1mo ago against content hash 833ec6b43b28, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions: Skills Repo

This is the source repository for Claude Code and Codex skills. Skills are installed from here to ~/.agents/skills/ (the canonical universal path) and symlinked into ~/.claude/skills/ (Claude Code) via npx skills.

Critical Rule: Never Edit Installed Files

Installed skill files are build artifacts. Do not modify them directly.

Location	What it is	Editable?
`plugins/<skill>/`	Source of truth	YES, edit here
`~/.agents/skills/<skill>/`	Installed copy (canonical, read by Codex and other universal clients)	NO, reinstall to update
`~/.claude/skills/<skill>/`	Symlink into `~/.agents/skills/<skill>/`	NO, reinstall to update

If you edit ~/.claude/skills/slipbox/SKILL.md instead of plugins/slipbox/SKILL.md, your changes will be lost the next time the skill is installed and will never reach other machines.

Workflow for Skill Changes

Edit files under plugins/<skill>/.
Run ./scripts/validate-skills.sh.
Commit and push to main when the requested workflow authorizes it.

Reinstall on each machine (always use -g for global install):

npx skills add randroids-dojo/skills --skill <name> -y -g

Do not rely on npx skills update: the installed skills have an empty skillFolderHash in ~/.agents/.skill-lock.json, so the CLI cannot detect changes and will always report "All skills are up to date". Always use npx skills add to pull the latest.

Repository Structure

plugins/
├── blender-production/
├── godot/
├── randroid/
│   ├── SKILL.md          # Thin workflow router
│   ├── skills/           # Focused portable workflows
│   │   ├── randroid-loop/
│   │   ├── randroid-address-pr-comments/
│   │   ├── randroid-vibereview/
│   │   ├── randroid-clean-slop/
│   │   └── randroid-game-feel/
│   ├── commands/         # Legacy Claude aliases
│   ├── hooks/
│   └── .claude-plugin/
├── slipbox/
│   ├── SKILL.md          # Concise portable entrypoint
│   └── references/       # Conditional detail
├── spiral/
├── task-tracking-dots/
└── unreal/

Read the full file on GitHub · 82 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.

1mo ago Changed · +112 tokens per session 833ec6b43b28
1mo ago Changed · +2 lines · +18 tokens per session c40572959562
2mo ago Changed · +15 lines · +226 tokens per session 7a1a39032316
2mo ago First seen · 65 lines · 668 tokens per session scan A 8569e501f17c

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository Randroids-Dojo/skills (46 stars, last pushed today), licensed MIT. It adds 1,024 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 2026-08-30.

skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills AGENTS.mdRandroids-Dojo/skills	Instructions file	46	today	MIT	A	1,024	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

skills: Instructions file for Codex