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 agentmods add skills/spacezephyr/cowrite/article-batch-illustrationnpx skills add SpaceZephyr/cowrite --skill article-batch-illustrationgit clone --depth 1 https://github.com/SpaceZephyr/cowriteWrote 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/spacezephyr/cowrite/article-batch-illustration)<a href="https://agentmods.dev/skills/spacezephyr/cowrite/article-batch-illustration"><img src="https://agentmods.dev/badge/skills/spacezephyr/cowrite/article-batch-illustration.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00933 |
| Opus 5 | $0.00032 | $0.00466 |
| Sonnet 5 | $0.00013 | $0.00187 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
article-batch-illustration 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 6d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Batch Illustration for Cowrite
Plan and generate a coherent illustration set for one complete Cowrite Markdown page. This Skill owns article analysis and placement. The bundled image-studio Skill owns prompt assembly and generation through Codex's built-in image_gen tool.
Fixed Cowrite profile
- Output: PNG, 16:9, 2K
- Image type: image-studio type D / article logic illustration
- Generation path: Codex built-in
image_gentool only; one tool call per image - Language: Simplified Chinese; technical abbreviations may remain English
- Count: normally 2-6; use fewer for short articles
- Placement: after an exact, unique Markdown heading or paragraph anchor
- Page safety: never rewrite the source article; insert only successful final images
Never use LabNana, Gemini, an API/CLI image generator, an embedded API key, web image search, or another model. If built-in image_gen is unavailable or fails, report the failure and leave the page unchanged.
Phase 1: analyze and select positions
- Read the latest Cowrite page through
cowrite_get_page. - Ignore frontmatter, references, footnotes, existing delivery links, and existing images whose alt text starts with
文章配图. - Split primarily on H2/H3 headings. For heading-free prose, use major topic transitions.
- For every candidate, record:
- exact unique anchor from the current Markdown;
- one-sentence core point;
- 3-5 key concepts;
- best structure: concept, flow, comparison, hierarchy, relationship, or matrix.
- Select only positions where a diagram materially improves comprehension. Do not illustrate every section and do not create decorative filler.
- Keep the set between 2 and 6 unless the article is too short. Prefer fewer, stronger images.
Phase 2: establish one visual system
Choose one image-studio style for the whole set based on the article:
- product/general explanation:
minimalornotion - data/research:
editorial-infographicorscientific - technical systems:
blueprint - education/personal narrative:
sketch-notes - culture/aesthetics:
chinese-elegance
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.
- 6d ago First seen · 67 lines · 63 tokens per session scan A 158286300dc1
article-batch-illustration is a skill published in the GitHub repository SpaceZephyr/cowrite (91 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 933 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…