skern: Instructions file for Codex

AGENTS.md

skern AGENTS.md is an instructions file for Codex, OpenCode from devrimcavusoglu/skern. It costs 4,349 tokens per session, scanned B, original, Apache-2.0.

Repository instructions for skern, a Go command-line tool that stores and manages reusable instructions for coding agents in SKILL.md files. It describes the project structure, supported commands, and development decisions.

In plain words
What is it for?
Use it when developing skern, especially for registry commands such as creating, importing, searching, validating, showing, comparing, or removing skills.
Why use it?
It gives an agent the project context and rules it needs before changing skern, reducing guesswork about where code belongs and how it should be checked.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; reads ~/.codex paths; mentions AGENTS.md.

This is devrimcavusoglu/skern's own configuration. It tells Codex and OpenCode how to work on skern itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skern configures →

Reuse

Borrowing it

Nothing to install: this file belongs to devrimcavusoglu/skern. 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/devrimcavusoglu/skern/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/devrimcavusoglu/skern

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.

agentmods badge for skern AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/devrimcavusoglu/skern/agents-md/github.svg)](https://agentmods.dev/instructions/devrimcavusoglu/skern/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/devrimcavusoglu/skern/agents-md"><img src="https://agentmods.dev/badge/instructions/devrimcavusoglu/skern/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.

agentmods 80×15 button for skern AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/devrimcavusoglu/skern/agents-md"><img src="https://agentmods.dev/badge/instructions/devrimcavusoglu/skern/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,349 This file is loaded in full into every session.
When invoked 4,349 The same file — it is already loaded in full.
Security scan B 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04349 $0.04349
Opus 5.5 $0.01740 $0.01740
Sonnet 5.5 $0.00870 $0.00870
Haiku 4.5 $0.00435 $0.00435

Measured 2mo ago against content hash 87464af57700, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

skern AGENTS.md scanned grade B 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 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

| Per-platform capacity (project scope) | Count in the platform's project skills dir (e.g. `.claude/skills/`) | Warn at >= 20 |
AGENTS.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Skern Development Guide

Conventions, architecture, and design decisions for agents working in this repo. Human contributor setup — the full build/test matrix, directory tree, and dependency list — lives in docs/contributing/development.md. Release history lives in CHANGELOG.md; neither is restated here.

Project Overview

Skern is a minimal, agent-first CLI for managing Agent Skills across agentic development platforms. It follows the Agent Skills open standard (agentskills.io) and uses SKILL.md files with YAML frontmatter as the canonical format.

Written in Go 1.25+. Latest release v0.4.0; main carries unreleased work (see the [Unreleased] section of the CHANGELOG).

Scope

The registry is the center of gravity. Skern's value is being the single cross-platform source of truth for skills: one SKILL.md per skill, stored once, managed through skern regardless of which agent is running. Registry commands (create, import, edit, list, search, show, validate, version, diff, recommend, remove) are the primary surface, and skern init --instructions exists so an agent can be told to reach for skern directly instead of hunting through platform directories.

Platform install/uninstall is first-class and stays. Copying skills out to native platform directories serves real cases the registry alone does not: native progressive disclosure, sandboxed agents that cannot shell out to skern, and one-shot migration from an existing .claude/skills/. Adapters are maintained and extended, and adapter bugs are ordinary product bugs — they are just not the headline drive. The skern skill command tree encodes this split directly via two cobra groups: Registry commands and Platform commands (internal/cli/skill.go).

When proposing features, weigh them against the registry thesis first. New work that only makes sense as a per-platform copy needs a use case from the list above.

Read the full file on GitHub · 376 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.

  1. 2mo ago First seen · 376 lines · 4,349 tokens per session scan B 87464af57700

Subscribe to this mod's changes

skern AGENTS.md is an instructions file published in the GitHub repository devrimcavusoglu/skern (7 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 4,349 tokens to every session, about $0.0174 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

skern AGENTS.md compared with instructions from other repositories

skern AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skern AGENTS.mddevrimcavusoglu/skernInstructions file72mo agoApache-2.0B4,349Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode