skills AGENTS.md

skills AGENTS.md is an instructions file for Codex, OpenCode from ikkeseb/skills. It costs 567 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining the ikkeseb skills collection. They define where skills and agent instructions live, how they are structured, and which file is authoritative.

In plain words
What is it for?
Use them when adding or updating skills, agent definitions, plugin manifests, or repository-wide instructions.
Why use it?
They reduce confusion about which files to edit and help keep skills, plugin manifests, and documentation consistent.

Instructions file for CodexOpenCode

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 instructions/ikkeseb/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/ikkeseb/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.

agentmods badge for skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ikkeseb/skills/agents-md.svg)](https://agentmods.dev/instructions/ikkeseb/skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ikkeseb/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ikkeseb/skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 567 This file is loaded in full into every session.
When invoked 567 The same file — it is already loaded in full.
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 $0.00567 $0.00567
Opus 5 $0.00283 $0.00283
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00057 $0.00057

Measured 4d ago against content hash f2a3188a0898, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 4d 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 · 25 lines

How it starts

The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Agent instructions for this repository.

Instruction source

AGENTS.md is canonical for every harness. CLAUDE.md is a one-line import adapter (@AGENTS.md) so Claude Code loads this file; Codex CLI reads it natively. Edit here, never in CLAUDE.md.

This is a skills repository — a collection of agent skills published as a Claude Code plugin (ikkeseb-skills) via .claude-plugin/plugin.json, with selected skills also usable from Codex CLI via .codex-plugin/plugin.json.

Structure

Each skill lives in skills/<name>/ with a SKILL.md whose YAML frontmatter (name, description, optional allowed-tools) is how Claude Code discovers the skill. Other files in the skill folder (references, scripts, assets) load on demand: keep the core workflow in SKILL.md, put branch-only or bulky reference in sibling files, and word each pointer to say when to read it. Top-level agents/ ships subagent definitions. The two plugin manifests carry one repository-wide release version.

Conventions

  • All repository content — every SKILL.md, reference file, and this AGENTS.md — is written in English, whatever language a session converses in. (A skill's runtime output follows the session; the committed artifacts stay English.)
  • Skills publish publicly via the marketplace, so keep content free of private or sensitive detail, don't personalize instructions, and don't hard-wire a skill's logic to a specific private repo. Standard public repository attribution is the only identity exception.
  • Skills are self-contained: a SKILL.md body never depends on another skill's semantics; a description: may name a sibling solely for trigger disambiguation.
  • bash scripts/check-repo.sh is the aggregate static and runtime gate; run the checks required by the changed surface.

Maintainer sessions

If a local/ directory exists here, you are on a maintainer machine: read local/AGENTS.md and local/STATUS.md before starting work, and local/MAINTAINING.md before changing shipped content — release procedure, the add/rename/remove sync lists, frontmatter policy and authoring conventions live there, not in this file. local/ is a separate nested private git repo (not a submodule), gitignored here, so a clone or plugin install simply won't have it — for such sessions the conventions above plus check-repo are the whole contract. A git ask that doesn't name a target ("pull both repos") covers this repo and local/. Never run git clean -x variants in this repo; they delete it.

Read the full file on GitHub · 25 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. 4d ago First seen · 25 lines · 567 tokens per session scan A f2a3188a0898

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository ikkeseb/skills (2 stars, last pushed yesterday), licensed MIT. It adds 567 tokens to every session, about $0.0028 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.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 5,182 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,733 tokens