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/tmchow/illo-skill/illonpx skills add tmchow/illo-skill --skill illogit clone --depth 1 https://github.com/tmchow/illo-skillWhat 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 | $0.00169 | $0.11884 |
| Opus 5 | $0.00084 | $0.05942 |
| Sonnet 5 | $0.00034 | $0.02377 |
| Haiku 4.5 | $0.00017 | $0.01188 |
Grade A, and why
illo 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 yesterday.
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 — 720 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Illo
Make original, distinctive editorial illustrations for written content. One
image explains one idea: a key judgment, a flow, a before/after, a trap, a
loop. A recurring mascot is the one performing the idea in every scene —
the subject, never decoration. When one idea advances through stages, it can
be a mini-comic: 2–4 panels inside a single image. And when the idea is
itself a traceable structure — a pipeline, labeled stages, a fan-out, a
timeline, a loop — it can be an explainer: the same mascot and look
drawing the structure as a hand-built sketch-diagram with arrows and
callouts (references/composition.md, "Two registers" and "Pick the
diagram type"; editorial scene is always the default). A named pipeline
or recipe is labeled stages inside that register — named phases in
order, one connected system, pack-solved for this body, never a new look.
Or a character cutout: the mascot alone on a transparent PNG for downstream overlay
— pose and contact continuity only, no idea, no text, no environment
(references/cutout.md).
This is a configurable house style, not a generic image generator. The
methodology is the constant; the character pack and palette are the
parameters — and a character pack carries its style with it: one look
per pack, chosen from the bundled look library (riso — grainy halftone,
ink-layer offset, paper grain, one bold softly-rounded outline — plus
blueprint, woodcut, pixel, clay, manila, chalk, phosphor, enamel,
gouache, felt, diorama, sketchbook, bricks, fizz, bloom, and snes) or a custom style file. The default mascot is
Blot, a deadpan ink-drop in riso. Palettes come
from presets, the user's own palette file, or one derived color. Whatever the
parameters, it is intentionally not a photo — with one deliberate exception, the
bricks look, a toy-brick photography style — not a logo, not a corporate
infographic, not a formal boxes-and-diamonds flowchart look, not a UI
mockup. Asking for a flowchart still means labeled stages in the pack's
look — the formality ban is a look constraint, not a refusal of the word.
What ships with it
37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/character-reference-pixel.png 107 KB
- assets/character-reference.webp 165 KB
- assets/checksums.txt 416 B
- NOTICE 703 B
- README.md 18 KB
- references/article-set-character-reroute.md 3.8 KB
- references/backends.md 17 KB
- references/character-builder.md 13 KB
- references/character.md 11 KB
- references/composition.md 34 KB
- references/cutout.md 15 KB
- references/models.md 4.4 KB
- references/pack-sharing.md 6.5 KB
- references/palettes.md 5.3 KB
- references/prompt-recipe.md 17 KB
- references/quality-bar.md 18 KB
- references/styles/bloom.md 5.5 KB
- references/styles/blueprint.md 2.9 KB
- references/styles/bricks.md 6.5 KB
- references/styles/chalk.md 2.8 KB
- references/styles/clay.md 3.6 KB
- references/styles/diorama.md 5.4 KB
- references/styles/enamel.md 3.9 KB
- references/styles/felt.md 5.4 KB
- references/styles/fizz.md 5.2 KB
- references/styles/gouache.md 3.1 KB
- references/styles/manila.md 3.2 KB
- references/styles/phosphor.md 3.0 KB
- references/styles/pixel.md 2.9 KB
- references/styles/sketchbook.md 6.8 KB
- references/styles/snes.md 8.4 KB
- references/styles/woodcut.md 2.6 KB
- references/surprise.md 28 KB
- references/visual-style.md 3.4 KB
- scripts/diagram_route.py 25 KB runs code
- scripts/illo.py 98 KB runs code
- scripts/repair-hermes-assets.sh 2.1 KB runs code
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.
- yesterday First seen · 720 lines · 169 tokens per session scan A 592503f91a15
illo is a skill published in the GitHub repository tmchow/illo-skill (358 stars, last pushed 3d ago), licensed MIT. It adds 169 tokens to every session and 11,884 once invoked, about $0.0008 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
ian-xiaohei-illustrations
生成 Ian 风格的中文正文配图。用于用户要求为中文文章、帖子、博客、Notion 文档、工作流文档、方法论、流程、结构、状态、隐喻或观点生成“怪诞”“小黑”“手绘”“正文配图”“文章插图”“配图建议”“shot list”“去标题/改图”等任务;默认使用小黑 IP、纯白手绘、少量红橙蓝批注、简洁清爽但天马行空的视觉风格。.
vision-review
免费读图与视觉检查。当用户要分析、识别、检查或描述图片/截图,检查界面或布局的视觉问题(文字重叠、溢出、错位),检测水印/Logo,或把图片内容转成文字时使用。引擎链:智谱 GLM-4V-Flash(免费首选)→ DeepSeek-V4-Flash-Vision-Exp(与主 agent 同 key,付费可选)→ SenseNova / SiliconFlow Qwen3-VL / Google Gemini 备用;key 取自环境变量、/.dsh/.credentials.yaml 或 /.dsh/secrets/media-tools.env,永不写进 skill。.
media-tools
免费生成图片。当用户要生成图片、插画、头像、背景、banner 等(包括付费图片额度不可用时)使用。优先 SenseNova U1 Fast,其次 SiliconFlow Kolors;key 取自环境变量、/.dsh/.credentials.yaml 或 /.dsh/secrets/media-tools.env,永不写进 skill。.
photo-revival
Turn ordinary photos or everyday snapshots into poetic hand-drawn illustrations with large white-paper negative space, vivid localized color, subtle collage accents, and tiny handwritten captions. Use when a user wants a real photo reimagined as an illustration rather than filtered, beautified, or photorealistically…
taxue-creative-style
踏雪影像风格引擎。四种能力:①按风格库出图(文人水墨、留白海报、城市卡、治愈插画、上美影、剪纸、纸雕、日式杂志、写实胶片、CCD、影棚人像、踏雪寻仙、层叠城市、剪纸新中式、3D书法、金石篆刻、器物禅意、赛博东方等签名风格;金融隐喻走 F8-V8 或纪念碑参考模板)②优化任意已有提示词(七维诊断打分+修复+注入踏雪DNA)③元提示词创作(任意需求从零构建精确提示词,保持踏雪独到影像风格)④学习用户偏好(记录使用历史与反馈,下次路由优先匹配)。子技能路由:个人 IP 插画、民国漫画杂志、面向领导生图、图片反推(见正文 §0)。触发:踏雪风格、taxue…
codex-imagegen
Generate or edit images via the Codex CLI's built-in $imagegen skill (gpt-image-2). Use this skill when the user needs visual assets saved to disk — icons, banners, illustrations, OG images, infographics, diagrams, hero art, placeholder images, transparent-background cutouts, or photo edits — in PNG/JPEG/WebP format.…