What is ai-agent-skills AGENTS.md?

A set of repository instructions for AI agents working on OpenLinkSoftware/ai-agent-skills. It defines which guidance takes priority, how to use the repository's RDF memory files, and rules such as not inventing URLs.

Use it when an AI agent works in that repository and needs to inspect its instructions, memory files, folder structure, and precedence rules.

It gives agents a consistent way to follow project-specific policies and retrieve or update shared task memory.

How OpenLinkSoftware/ai-agent-skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to OpenLinkSoftware/ai-agent-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/OpenLinkSoftware/ai-agent-skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/OpenLinkSoftware/ai-agent-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/openlinksoftware/ai-agent-skills/agents-md/github.svg)](https://agentmods.dev/instructions/openlinksoftware/ai-agent-skills/agents-md)

Your own site

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

Per session 5,297 This file is loaded in full into every session.

When invoked 5,297 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.05297	$0.05297
Opus 5.5	$0.02119	$0.02119
Sonnet 5.5	$0.01059	$0.01059
Haiku 4.5	$0.00530	$0.00530

Measured 1mo ago against content hash 5f66e8ad79b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-agent-skills AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

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

2. **Computed with a tool** — e.g., a Python script for pako encoding, `curl` for endpoint discovery

AGENTS.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

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

MANDATORY: Agent RDF Memory Protocol (Execute Before Every Task)

This instruction takes precedence over all other guidance in this file.

Before responding to any user request, you MUST execute this retrieval sequence:

List agent-rdf-memory/ and all subfolders (sessions/, projects/, entities/)
Read agent-rdf-memory/core.ttl
Read agent-rdf-memory/preferences.ttl
Read agent-rdf-memory/index.ttl
Follow index.ttl references to any relevant session, project, or entity files
Reason over the loaded Turtle content before proceeding

After completing any meaningful task:

Generate valid RDF-Turtle and write to the appropriate file in agent-rdf-memory/ (see folder structure and rules below)
Never store memory in context, comments, or any other location

If agent-rdf-memory/ is inaccessible, report it as a critical error immediately.

Precedence Hierarchy

preferences.ttl — the queryable source of truth for operational preferences
This file (AGENTS.md) — prose reference and policy
Unstated defaults — lowest priority

When preferences.ttl contradicts prose in this file, preferences.ttl wins.

No Fabricated URLs

Never fabricate, guess, construct, or hallucinate any URL. This prohibition is absolute and covers every URL type: encoded live-editor links (pako, base64), API endpoints, documentation pages, download links, image URLs, resolver links, and any other URI.

A URL is only acceptable if produced by one of these methods:

Verbatim — copied exactly from a source the user provided
Computed with a tool — e.g., a Python script for pako encoding, curl for endpoint discovery
Validated pattern — constructed from a known, documented pattern where every path component is verified

If none of these apply, omit the URL and ask the user for the correct one. A fabricated URL that renders a blank page, a 404, or wrong content is worse than no URL at all. After computing an encoded URL with a tool, verify it actually works before including it in any document.

Read the full file on GitHub · 345 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 · +27 lines · +612 tokens per session 5f66e8ad79b2
2mo ago First seen · 318 lines · 4,685 tokens per session scan A 1843da3f8501

Subscribe to this mod's changes

ai-agent-skills AGENTS.md is an instructions file published in the GitHub repository OpenLinkSoftware/ai-agent-skills (42 stars, last pushed 2d ago), licensed MIT. It adds 5,297 tokens to every session, about $0.0212 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

ai-agent-skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-agent-skills AGENTS.mdOpenLinkSoftware/ai-agent-skills	Instructions file	42	2d ago	MIT	A	5,297	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

ai-agent-skills: Instructions file for Codex