verse-to-prompt

verse-to-prompt is a skill for Claude Code from augchan42/inkstone. It costs 58 tokens per session (5,252 once invoked), scanned A, original, MIT.

A tool that turns classical Chinese poetry and other traditional verses into English prompts for image-generation systems.

In plain words
What is it for?
Use it to visualize Yilin, I Ching, Tang poetry, or similar classical Chinese text as generated artwork.
Why use it?
It gives the verse a planned visual interpretation and supports several defined artistic styles, including ink painting and tech-noir.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the inkstone plugin — 21 skills, 1 hook shipped together

Good fit Use it to visualize Yilin, I Ching, Tang poetry, or similar classical Chinese text as generated artwork.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/augchan42/inkstone/verse-to-prompt
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.

Any agent
npx skills add augchan42/inkstone --skill verse-to-prompt
Clone the repo
git clone --depth 1 https://github.com/augchan42/inkstone

Made for: Claude Code.

Or install inkstone, the plugin that ships this one along with the rest of its 21 skills, 1 hook.

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 verse-to-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/augchan42/inkstone/verse-to-prompt/github.svg)](https://agentmods.dev/skills/augchan42/inkstone/verse-to-prompt)
Your own site
<a href="https://agentmods.dev/skills/augchan42/inkstone/verse-to-prompt"><img src="https://agentmods.dev/badge/skills/augchan42/inkstone/verse-to-prompt/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.

agentmods 80×15 button for verse-to-prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/augchan42/inkstone/verse-to-prompt"><img src="https://agentmods.dev/badge/skills/augchan42/inkstone/verse-to-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,252 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00058 $0.05252
Opus 5 $0.00029 $0.02626
Sonnet 5 $0.00012 $0.01050
Haiku 4.5 $0.00006 $0.00525

Measured 10d ago against content hash 7d0d852c562f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

verse-to-prompt 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 10d 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.

skills/verse-to-prompt/SKILL.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verse → Image Prompt

Convert a classical Chinese verse into an English image generation prompt, following validated composition rules developed across 4,096 images for SixLines.online.

Mode Selection

  • Default (ink painting): Classical ink painting aesthetic.
  • Stipple (--stipple flag): The production matrix skin — luminous golden-age sci-fi stipple. This is the actual style of the 4,096 matrix-skin images on SixLines.online (ADR-173). It reuses the ink-painting scene verbatim and only swaps the render suffix.
  • Tech-noir (--tech-noir flag): An experimental phosphor-green CRT cyberpunk reinterpretation. Not the production matrix look — it re-renders the scene in a tech register. Use only when you specifically want that alternative.

Routing:

  • --stipple, or "matrix skin", "stipple", "phosphor stipple", "the actual matrix images" → Stipple Mode
  • --tech-noir, or "tech-noir", "CRT cyberpunk", "phosphor-green reinterpretation" → Tech-Noir Mode
  • otherwise → Ink Painting Mode

Note: "matrix skin" maps to Stipple, not Tech-Noir — the shipped matrix images are stipple.


INK PAINTING MODE (default)

Your Task

Given a verse (raw text, any format), produce:

  1. A style classification with a one-line rationale
  2. A 50-60 word English prompt ending with "Chinese ink painting."
  3. A faithful English translation of the verse

The 5 Style Categories

Style Palette & Feel Use When Verse Contains
atmospheric-night Dark palette, strong light source in darkness Darkness, isolation, winter, grief, hidden things, fear, cold, sleeplessness
ink-landscape Classic shanshui, depth corridors, water/mountain Nature, seasons, water, agriculture, travel, weather, rivers, mountains
figures-in-mist Ink wash + soft watercolor tints, human scale Narrative, marriages, courts, travelers, families, ceremonies, human emotion
bold-action Dynamic diagonals, warm ochre palette, kinetic energy Animals, combat, hunts, dramatic journeys, storms, military, physical struggle
cosmic-night Deep blue/black + gold/white, celestial elements Stars, heaven, mythical beasts, cosmic order, immortals, divination, emperors

Read the full file on GitHub · 288 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. 10d ago First seen · 288 lines · 58 tokens per session scan A 7d0d852c562f

Subscribe to this mod's changes

verse-to-prompt is a skill published in the GitHub repository augchan42/inkstone (4 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 5,252 once invoked, about $0.0003 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 skills, from other repositories

analyze-video

Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template for the Novoads API. The output is a new formula file — like seedance-2-ugc.md — that captures the video's structure, pacing, camera work, edit style and tone so it can be recreated with any product, any person, in…

novoads/agent-skills · 138 tokens

midjourney-prompting

Expert Midjourney prompt engineering skill. Use this skill when users need help crafting effective Midjourney prompts, converting natural language descriptions into optimized prompts, or want guidance on Midjourney parameters and techniques. Specializes in V7 best practices, the 7-Element Framework, and photography…

leggiemint/legnext-skills · 67 tokens

seedance-examples-ja

This skill should be used when the user asks for Japanese Seedance 2.0 examples, Japanese prompt patterns, example rewrites, or safe versions of working Japanese video-generation prompts.

Emily2040/seedance-2.0 · 43 tokens

seedance-filter

This skill should be used when a Seedance 2.0 prompt is blocked or rejected, when moderation is a suspected cause of a problem, or when the user asks for a content-boundary review or safer alternative. Assess the actual request before offering a clarification.

Emily2040/seedance-2.0 · 57 tokens

seedance-prompt-short

This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.

Emily2040/seedance-2.0 · 47 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens