What is olegvg-skills AGENTS.md?

Repository instructions for olegvg-skills, a markdown-only collection of reusable skills, commands, templates, documentation, and installation manifests. They explain how skills are grouped and kept separate from the user's knowledge base.

Use them when adding, moving, or organizing skills, plugins, manifests, templates, or documentation in this collection.

They prevent changes from placing files in the wrong group or coupling the repository to user-specific knowledge-base data.

How olegvg/olegvg-skills configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to olegvg/olegvg-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/olegvg/olegvg-skills/master/AGENTS.md

Clone the repo

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

Made for: Claude Code, 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/olegvg/olegvg-skills/agents-md/github.svg)](https://agentmods.dev/instructions/olegvg/olegvg-skills/agents-md)

Your own site

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

Per session 1,144 This file is loaded in full into every session.

When invoked 1,144 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	$0.01144	$0.01144
Opus 5	$0.00572	$0.00572
Sonnet 5	$0.00229	$0.00229
Haiku 4.5	$0.00114	$0.00114

Measured 9d ago against content hash f3a925b320c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

olegvg-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 9d 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for Claude Code, Codex, and other coding agents working in this repository.

What This Repo Is

A grouped personal skill repository for Claude Code, Codex, and Vercel Skills CLI. It is markdown-only: no build system, no test suite, no package manager. The deliverable is skills, commands, templates, docs, and install manifests.

Always-On Rules

.kb/ lives inside the user's corpus, never inside this plugin. Any change that couples .kb/ to this plugin location is wrong.
Runtime skills under skills/ are the source of truth for the olegvg-skills umbrella package. A standalone plugin under plugins/<plugin-name>/ is self-contained and is exposed by paired manifests: .codex-plugin/plugin.json plus an entry in .agents/plugins/marketplace.json for Codex, and .claude-plugin/plugin.json plus an entry in the root .claude-plugin/marketplace.json for Claude Code.
kb-for-agents must stay KB-only. General-purpose skills belong in core-dev or a future non-KB group.
Every public root skill under skills/ belongs to exactly one concrete group in .claude-plugin/marketplace.json and also appears in the olegvg-skills umbrella entry. Skills bundled inside a standalone plugin are owned by that plugin and must not be duplicated in the root groups or any skills array — they cannot work without the plugin runtime.
Vercel Skills CLI can show only one visible group per skill. Keep the umbrella entry first and concrete groups after it; umbrella install is --skill '*' or selecting all concrete groups interactively.
CLAUDE.md is a symlink to this file. Update AGENTS.md; do not create divergent Claude-only instructions.
Every version bump requires a matching pushed git tag, e.g. manifest 0.6.0 must ship with tag v0.6.0; the desktop release workflow depends on tag pushes.

Progressive Disclosure

Read only the file needed for the task before editing:

Before changing install commands, plugin manifests, marketplace metadata, or skills.sh grouping, read docs/agent-instructions/install-surfaces.md.
Before adding or editing skills, groups, command shims, or skill packaging metadata, read docs/agent-instructions/skill-authoring.md.
Before changing kb-* behavior, templates, or KB rationale docs, read docs/agent-instructions/kb-pattern.md.
Before bumping versions, tagging releases, or changing release packaging, read docs/agent-instructions/release-versioning.md.

Read the full file on GitHub · 69 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.

9d ago First seen · 69 lines · 1,144 tokens per session scan A f3a925b320c1

Subscribe to this mod's changes

olegvg-skills AGENTS.md is an instructions file published in the GitHub repository olegvg/olegvg-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 1,144 tokens to every session, about $0.0057 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.

ai-agents ai-awesome ai-memory-system

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

olegvg-skills: Instructions file for Claude Code