What is promptfiles AGENTS.md?

A set of instructions for working in the promptfiles repository, which stores AI skills and agent definitions as Markdown files. It explains the project layout, file conventions, plugin manifests, and local installation.

Use it when maintaining promptfiles, managing Claude Code or Codex installations, editing manifests, or understanding how its static Markdown files are organised.

It gives coding agents the repository-specific rules they need before editing files or changing installed skills and agents.

How sleeyax/promptfiles configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sleeyax/promptfiles. 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/sleeyax/promptfiles/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sleeyax/promptfiles

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/sleeyax/promptfiles/agents-md/github.svg)](https://agentmods.dev/instructions/sleeyax/promptfiles/agents-md)

Your own site

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

Per session 1,506 This file is loaded in full into every session.

When invoked 1,506 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	$0.01506	$0.01506
Opus 5.5	$0.00602	$0.00602
Sonnet 5.5	$0.00301	$0.00301
Haiku 4.5	$0.00151	$0.00151

Measured 2mo ago against content hash c3f7735f7fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

promptfiles 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to AI agents when working with code in this repository.

Project Overview

This is a curated collection of AI skills and agent definitions. There are no build steps, tests, or dependencies — the repository contains only static markdown files with YAML frontmatter.

Agents are Claude Code subagents, installed by symlinking into ~/.claude/agents/; scripts/install-codex-agents.sh generates Codex TOML equivalents from the same markdown files. Skills (used as Claude Code's replacement for slash commands in this repo) are installed via the skills npm CLI.

The repo also doubles as a Claude Code marketplace hosting one plugin, sleeyax-skills@sleeyax, that bundles every skill, both agents, and the output styles. See Plugin manifests.

Managing the local install

Prefer the skills CLI for anything that changes what is installed on the user's machine. Global installs live in ~/.agents/skills/<name>/, and each agent directory symlinks to them.

npx skills list -g                          # what is installed globally
npx skills add . -s '*'                     # install every skill from this working copy
npx skills add . -l                         # list what's installable here, without installing
npx skills update -g                        # pull the latest versions
npx skills remove --global <name>... -y     # uninstall by skill name

Install from ., not from sleeyax/promptfiles — the latter pulls the published GitHub copy and silently ignores uncommitted local work.

remove and add are interactive by default, but the CLI detects it is running under an agent and falls back to a non-interactive run. Pass -y anyway so the command can't block. -y on add also skips the scope prompt and auto-detects, so pass -g alongside it when the target is the global install.

If the CLI can't do the job — it's unavailable, the command fails, or the install is in a state it won't reconcile — edit ~/.agents/skills/ and the symlinks under ~/.claude/skills/ directly, and say that you did. Leave no dangling symlinks behind.

Read the full file on GitHub · 80 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 · 80 lines · 1,506 tokens per session scan A c3f7735f7fc7

Subscribe to this mod's changes

promptfiles AGENTS.md is an instructions file published in the GitHub repository sleeyax/promptfiles (4 stars, last pushed 2d ago), licensed MIT. It adds 1,506 tokens to every session, about $0.0060 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.

promptfiles AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
promptfiles AGENTS.mdsleeyax/promptfiles	Instructions file	4	2d ago	MIT	A	1,506	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
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 ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

promptfiles: Instructions file for Codex