Borrowing it
Nothing to install: this file belongs to rornic/zweig. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rornic/zweig/main/AGENTS.mdgit clone --depth 1 https://github.com/rornic/zweigWrote 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.
[](https://agentmods.dev/instructions/rornic/zweig/agents-md)<a href="https://agentmods.dev/instructions/rornic/zweig/agents-md"><img src="https://agentmods.dev/badge/instructions/rornic/zweig/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.
<a href="https://agentmods.dev/instructions/rornic/zweig/agents-md"><img src="https://agentmods.dev/badge/instructions/rornic/zweig/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00578 | $0.00578 |
| Opus 5.5 | $0.00231 | $0.00231 |
| Sonnet 5.5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
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 1mo 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.
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'sversion..claude-plugin/marketplace.json— Claude Code marketplace listing. Does not duplicateversion; plugin.json wins under strict mode..codex-plugin/plugin.json— Codex plugin manifest, mirrors.claude-plugin/plugin.jsonplus askillsfield 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— manualworkflow_dispatch(Actions tab, choose patch/minor/major) that bumps bothplugin.jsonversions, commits, tagsvX.Y.Z, and creates the GitHub release. Pushes straight tomain; there's no branch protection to route around.
Making changes
- Run
claude plugin validate . --strictbefore committing changes to either Claude manifest. - Cut a release with the
.github/workflows/release.ymlworkflow (Actions tab, pick patch/minor/major) when a change should reach existing installs; it bumps bothplugin.jsonversions, tags, and creates the GitHub release together. - Any non-trivial prose here (README, SKILL.md instructions) should go through this repo's own
zweig-writeandzweig-refineskills before it ships. - Don't add a shared file that a
SKILL.mdinstructs the model toReadat runtime: thatReadcall 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 ownSKILL.md, even if that duplicates it across skills. Companion files (likeEXAMPLE.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: ...).
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.
- 1mo ago First seen · 26 lines · 578 tokens per session scan A 59ad473eb4e3
zweig AGENTS.md is an instructions file published in the GitHub repository rornic/zweig (12 stars, last pushed 11d ago), licensed MIT. It adds 578 tokens to every session, about $0.0023 per session on Opus 5.5. 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.