AGENTS.base

AGENTS.base is an agent for coding agents from jeremylongworth-source/AgentSkills. It costs 0 tokens per session (91 once invoked), scanned A, original, MIT.

A base instruction file that explains where Codex skills are stored and when to use them. It also points to official OpenAI documentation for current Codex and API guidance.

In plain words
What is it for?
Locate skills, select matching guidance for a request, and verify current OpenAI model or API details.
Why use it?
It helps an AI coding agent find the right local instructions and avoid relying on outdated information about OpenAI products.

Agent

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 agents/jeremylongworth-source/agentskills/agents.base
Clone the repo
git clone --depth 1 https://github.com/jeremylongworth-source/AgentSkills

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 AGENTS.base

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongworth-source/agentskills/agents.base.svg)](https://agentmods.dev/agents/jeremylongworth-source/agentskills/agents.base)
Your own site
<a href="https://agentmods.dev/agents/jeremylongworth-source/agentskills/agents.base"><img src="https://agentmods.dev/badge/agents/jeremylongworth-source/agentskills/agents.base.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 91 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00091
Opus 5 $0.00000 $0.00046
Sonnet 5 $0.00000 $0.00018
Haiku 4.5 $0.00000 $0.00009

Measured 3d ago against content hash cb6a68373be7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AGENTS.base 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 3d 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/AGENTS.base.md · 7 lines

What it actually says

Skills files are available at $CODEX_HOME/skills or %USERPROFILE%\.codex\skills.

When a user request matches a local skill, prefer using the relevant skill instead of answering from memory alone. Read the skill's SKILL.md first, then load referenced files only when needed.

For current OpenAI model or API guidance, use openai-docs when installed and verify current facts from official OpenAI documentation.

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. 3d ago First seen · 7 lines · 0 tokens per session scan A cb6a68373be7

Subscribe to this mod's changes

AGENTS.base is an agent published in the GitHub repository jeremylongworth-source/AgentSkills (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 91 tokens. 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.