agentmods.dev

zweig AGENTS.md

zweig AGENTS.md is an instructions file for Codex, OpenCode from rornic/zweig. It costs 578 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents working on zweig, a self-hosted marketplace that distributes Claude Code and Codex CLI add-ons. They describe the repository's files, plugin formats, and shared skills.

In plain words
What is it for?
Use them when editing zweig's manifests, marketplace listings, skills, release workflow, or documentation.
Why use it?
They give an agent the project context and file conventions needed to make changes safely. They also record version and compatibility details that could otherwise be missed.

Instructions file for CodexOpenCode

not rated 11 13d ago A scan 578 tokens original MIT
View the source file rornic/zweig
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/rornic/zweig/agents-md
Clone the repo
git clone --depth 1 https://github.com/rornic/zweig

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 zweig AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rornic/zweig/agents-md.svg)](https://agentmods.dev/instructions/rornic/zweig/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rornic/zweig/agents-md"><img src="https://agentmods.dev/badge/instructions/rornic/zweig/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 578 This file is loaded in full into every session.
When invoked 578 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 $0.00578 $0.00578
Opus 5 $0.00289 $0.00289
Sonnet 5 $0.00116 $0.00116
Haiku 4.5 $0.00058 $0.00058

Measured 4d ago against content hash 59ad473eb4e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

zweig 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 · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI agents working in this repository.

What this repo is

A self-hosted plugin marketplace for both Claude Code and Codex CLI, shipping two writing skills, zweig-write and zweig-refine. Both plugin formats share the same skills/ directory. See README.md for what each skill does.

Structure

  • .claude-plugin/plugin.json — Claude Code plugin manifest, the single source of truth for that plugin's version.
  • .claude-plugin/marketplace.json — Claude Code marketplace listing. Does not duplicate version; plugin.json wins under strict mode.
  • .codex-plugin/plugin.json — Codex plugin manifest, mirrors .claude-plugin/plugin.json plus a skills field pointing at ./skills/.
  • .agents/plugins/marketplace.json — Codex marketplace listing, referencing this repo's plugin at ./ (path resolution to the repo root needs Codex CLI >= 0.142.0; older versions reject that path and need a subdirectory workaround instead).
  • skills/<name>/SKILL.md — skill definition (YAML frontmatter + instructions), shared by both plugin formats.
  • skills/zweig-refine/EXAMPLE.md — worked transcript of the refine loop.
  • .github/workflows/release.yml — manual workflow_dispatch (Actions tab, choose patch/minor/major) that bumps both plugin.json versions, commits, tags vX.Y.Z, and creates the GitHub release. Pushes straight to main; there's no branch protection to route around.

Making changes

  • Run claude plugin validate . --strict before committing changes to either Claude manifest.
  • Cut a release with the .github/workflows/release.yml workflow (Actions tab, pick patch/minor/major) when a change should reach existing installs; it bumps both plugin.json versions, tags, and creates the GitHub release together.
  • Any non-trivial prose here (README, SKILL.md instructions) should go through this repo's own zweig-write and zweig-refine skills before it ships.
  • Don't add a shared file that a SKILL.md instructs the model to Read at runtime: that Read call needs permission approval on every install, every time the skill fires, for every user. Content a skill always needs (style rules, cut criteria) must be inlined directly in that skill's own SKILL.md, even if that duplicates it across skills. Companion files (like EXAMPLE.md) are fine only for material a skill references but doesn't strictly require every run.
  • Commit messages: lowercase conventional commits (e.g. fix: ..., feat: ...).

Read the full file on GitHub · 26 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 · 26 lines · 578 tokens per session scan A 59ad473eb4e3

Subscribe to this mod's changes

zweig AGENTS.md is an instructions file published in the GitHub repository rornic/zweig (11 stars, last pushed 13d ago), licensed MIT. It adds 578 tokens to every session, about $0.0029 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.

Building agentsLLMaiclaudeclaude-codecodexprompt-engineering
Related

Other instructions, from other repositories

avoid-ai-writing CLAUDE.md

Instructions for conorbronsdon/avoid-ai-writing, covering claude.md, what this is, repository structure, how to make changes and architecture of the skill.

conorbronsdon/avoid-ai-writing · 812 tokens

TLDR CLAUDE.md

Instructions for 0p9b/TLDR, covering claude.md — tldr maintainer guide, product, source layout, edit rules and install paths.

0p9b/TLDR · 2,004 tokens

TLDR AGENTS.md

Instructions for 0p9b/TLDR: @./skills/tldr/SKILL.md @./skills/tldr-commit/SKILL.md @./skills/tldr-review/SKILL.md @./skills/tldr-compress/SKILL.md.

0p9b/TLDR · 45 tokens

Library-First-Engineering copilot-instructions.md

Instructions for StChiotis/Library-First-Engineering: You are an AI agent operating in a Library-First Engineering (LFE) repository. This adapter is a pointer. Canonical rules live in human-readable docs.

StChiotis/Library-First-Engineering · 366 tokens

prompt-improver AGENTS.md

Instructions for owenob1/prompt-improver: This repository packages prompt-improver as an Agent Skill.

owenob1/prompt-improver · 132 tokens

promptasy AGENTS.md

AGENTS.md instructions for romanticamaj/promptasy, covering agents.md — promptasy 工程 harness, 專案一句話, 每個 phase 的節奏, 測試金字塔（由快到慢） and 測試策略（成本控制的核心）.

romanticamaj/promptasy · 1,657 tokens