agentmods.dev

vibe-codex AGENTS.md

vibe-codex AGENTS.md is an instructions file for Codex, OpenCode from kks0488/vibe-codex. It costs 454 tokens per session, scanned A, original, MIT.

An AGENTS.md instruction file for vibe-codex, a project related to the Codex command-line tool. It describes repository conventions, skill files, scripts, and documentation practices.

In plain words
What is it for?
Use it to guide changes to scripts, skills, metadata, and documentation in the vibe-codex repository, including running its doctor script.
Why use it?
It gives coding agents consistent rules for maintaining the project and its distributable skills.

Instructions file for CodexOpenCode

not rated 11 20d ago A scan 454 tokens original MIT
View the source file kks0488/vibe-codex
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/kks0488/vibe-codex/agents-md
Clone the repo
git clone --depth 1 https://github.com/kks0488/vibe-codex

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 vibe-codex AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kks0488/vibe-codex/agents-md.svg)](https://agentmods.dev/instructions/kks0488/vibe-codex/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kks0488/vibe-codex/agents-md"><img src="https://agentmods.dev/badge/instructions/kks0488/vibe-codex/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 454 This file is loaded in full into every session.
When invoked 454 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 $0.00454 $0.00454
Opus 5 $0.00227 $0.00227
Sonnet 5 $0.00091 $0.00091
Haiku 4.5 $0.00045 $0.00045

Measured 3d ago against content hash a73f36732739, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vibe-codex 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 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.md · 26 lines

What it actually says

vibe-codex (Codex CLI)

This repo is Codex-first and keeps distributable skill sources under skills.

Repo conventions

  • Keep scripts/*.sh and scripts/*.ps1 feature-parity (same subcommands + flags).
  • Skills live in skills/<skill>/SKILL.md (+ optional agents/openai.yaml UI metadata + dependency hints; optional legacy SKILL.json). Tip: keep agents/openai.yaml JSON-formatted (JSON ⊂ YAML) so doctor scripts can validate without extra deps.
  • Current OpenAI documentation lists .agents/skills for local discovery. New installs should target .agents/skills via --agents; the root skills directory also supports plugin packaging.
  • For SKILL.md YAML frontmatter, keep name ≤ 64, description ≤ 1024, and metadata.short-description ≤ 1024.
  • When changing skills, keep SKILL.md ↔ agents/openai.yaml (and SKILL.json if present) aligned and run bash scripts/doctor.sh.
  • Avoid creating backup folders inside any skills directory (Codex loads skills recursively and backups can become duplicate skills).
  • Do not describe vc teams as Codex-native. It is a persistent mailbox companion; built-in Codex subagents perform actual in-session delegation.
  • Do not add guaranteed-success, infinite-retry, or never-ask instructions. Use bounded recovery and truthful blockers.

OpenAI docs

  • Prefer the OpenAI Developer Docs MCP server when you need up-to-date OpenAI/Codex/API info.
    • Setup: vc mcp docs (or codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp)

Handy commands

  • Diagnose: bash scripts/doctor.sh (or pwsh scripts/doctor.ps1)
  • Install skills: bash scripts/install-skills.sh [--agents] (or pwsh scripts/install-skills.ps1 [--agents])
  • MCP helpers: vc mcp docs, vc mcp skills, vc mcp list
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 · 26 lines · 454 tokens per session scan A a73f36732739

Subscribe to this mod's changes

vibe-codex AGENTS.md is an instructions file published in the GitHub repository kks0488/vibe-codex (11 stars, last pushed 20d ago), licensed MIT. It adds 454 tokens to every session, about $0.0023 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 2026-08-30.

agent-skillsautomationcodexcodex-clideveloper-toolsopenai
Related

Other instructions, from other repositories

codexia AGENTS.md

Instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.

milisp/codexia · 656 tokens

CodexPotter AGENTS.md

Instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.

breezewish/CodexPotter · 306 tokens

codex-howto AGENTS.md

Instructions for Phelan164/codex-howto, covering repository guidance, purpose, editing rules, validation and definition of done.

Phelan164/codex-howto · 285 tokens

codex-docs AGENTS.md

Instructions for chenrui333/codex-docs, covering agents notes, scope, generated content boundaries, local workflow and validation expectations.

chenrui333/codex-docs · 749 tokens

codex-status-bar AGENTS.md

Instructions for yuriipalam/codex-status-bar, covering repository instructions, engineering expectations, verification and release procedure.

yuriipalam/codex-status-bar · 862 tokens

ctxwise AGENTS.md

Instructions for FramY2/ctxwise, a project described as: CtxWise — see and control what Codex loads. Local-first context audit, profiles, drift detection, and honest token receipts.

FramY2/ctxwise · 144 tokens