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.
npx skills add rornic/zweig --skill zweig-writegit 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/skills/rornic/zweig/zweig-write)<a href="https://agentmods.dev/skills/rornic/zweig/zweig-write"><img src="https://agentmods.dev/badge/skills/rornic/zweig/zweig-write/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/skills/rornic/zweig/zweig-write"><img src="https://agentmods.dev/badge/skills/rornic/zweig/zweig-write.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 | $0.00000 | $0.00461 |
| Opus 5.5 | $0.00000 | $0.00184 |
| Sonnet 5.5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
zweig-write 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 11d 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.
What it actually says
Zweig Write
Write every sentence to survive the question zweig-refine asks later: cut this, does the reader lose something, or just words? A denser draft means that loop converges faster.
zweig-refine's loop and fresh-reader gate catch more than this skill can, since a drafting context can't see its own blind spots. Once a draft is ready, ask the user whether to run zweig-refine on it next, and run it only if they say yes.
Before drafting
Warnings, gotchas, failure modes, exact flags, commands, paths, versions, error strings, ordering, and context a reader landing mid-document needs: all of it has to survive into the first draft. Density is not a license to omit any of it.
While drafting, skip these on the way in
- Throat-clearing openers ("We wanted to let you know that...", "It's worth noting that...", "In terms of...").
- Restating what a heading, identifier, or the previous sentence already established.
- Hedge words that carry no information ("approximately", "generally", "as needed", "or so").
- The same point twice in different phrasing for emphasis.
- Boilerplate transitions ("Additionally,", "Furthermore,", "It should also be noted that").
- Decorative emoji in headings, bullets, or sign-offs. Keep one only when it carries meaning the words don't, like a pass/fail column in a status table.
One idea per sentence. Prefer fewer, denser points over broad coverage.
Punctuation
- No em dashes (—). Use a period, a comma, or parentheses first.
- Colons are a last resort, not a default way to introduce an example or elaboration. Try a period or comma before reaching for one.
- Semicolons are rare. Prefer a comma or two sentences unless the clauses are inseparable.
- One point per paragraph.
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.
- 11d ago Changed · +1 lines d40fed6b7c2a
- 1mo ago First seen · 32 lines · 0 tokens per session scan A 5ea86c7d763c
zweig-write is a skill published in the GitHub repository rornic/zweig (12 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 461 tokens. 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 skills, from other repositories
ai-engineering-toolkit
Overview of six AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
promptfoo-provider-setup
Connect Promptfoo to a model, live HTTP API, local Python/JavaScript provider, or app code. Use for request/auth mapping, response parsing, OpenAPI setup, and connection smoke tests. Use promptfoo-evals for broader eval coverage and promptfoo-redteam-setup for attack selection.
avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
voice-preserving-rewriter
Use when the user asks to rewrite, humanize, clean up, or remove AI-isms from text while preserving the writer's voice, facts, intent, structure, register, and protected material.
flux2-lora-training
Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks. Do not use for generic Stable Diffusion/DiT training, prompt authoring, or model serving; route those tasks to their specialized skill.