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 Neko3000/deepseek-whalechan --skill whalechan-image-charactergit clone --depth 1 https://github.com/Neko3000/deepseek-whalechanWrote 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/neko3000/deepseek-whalechan/whalechan-image-character)<a href="https://agentmods.dev/skills/neko3000/deepseek-whalechan/whalechan-image-character"><img src="https://agentmods.dev/badge/skills/neko3000/deepseek-whalechan/whalechan-image-character/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/neko3000/deepseek-whalechan/whalechan-image-character"><img src="https://agentmods.dev/badge/skills/neko3000/deepseek-whalechan/whalechan-image-character.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 | $0.00060 | $0.02425 |
| Opus 5.5 | $0.00024 | $0.00970 |
| Sonnet 5.5 | $0.00012 | $0.00485 |
| Haiku 4.5 | $0.00006 | $0.00243 |
Grade A, and why
whalechan-image-character 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 13d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whale-chan Image Character
Create verified Whale-chan PNGs. Preserve Whale-chan's permanent identity while resolving every visual dimension independently from the user's request, typed reference images, and canonical defaults. A custom value changes only its own field.
Workflow: propose → Gate 1: select directions → Gate 2: confirm scope and begin → expand, validate and freeze → generate, review and deliver. Selection alone is not permission to generate.
Load guidance as needed
- Read
references/proposal-selection.mdbefore presenting either gate or interpreting replies. - Read
references/assignment-schema.mdwhenever normalizing, confirming, or freezing a request. - Read
references/character-spec.mdbefore building prompts or deciding whether a requested customization preserves Whale-chan identity. - Read
references/form-profiles.mdwhen resolving or measuring proportions. The five bundled forms are recommended presets, not the only allowed ratios. - Read
references/reference-index.mdwhen selecting bundled or user-supplied references. - Read
references/provider-routing.mdbefore any provider call or parallel run. - Read
references/qa-rubric.mdbefore reviewing or promoting a candidate. - Read
references/gallery.mdbefore exporting the completed task's preview gallery. - Treat
references/reference-catalog.jsonas the machine-readable authority for bundled paths, hashes, preset ratios, and preset acceptance ranges.
Choose the language
Read references/language-policy.md before planning. Resolve one task language: explicit user instruction → meaningful current-session expression → newest meaningful local session within 24 hours → ask when uncertain. Use scripts/detect-language.py for historical evidence, not as an automatic verdict; recent sessions take precedence over aggregate counts.
Save the normalized BCP-47 tag, actual resolution evidence and any explicit scoped overrides. Use it for communication, image lettering, HTML UI, drawing prompts and visible run/image titles. Preserve exact locked wording and necessary technical tokens. Keep internal IDs and filenames in English. Propagate the saved language to workers and resume from it; never redetect during execution.
What ships with it
50 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.
- agents/openai.yaml 381 B
- assets/gallery/gallery.css 18 KB
- assets/gallery/gallery.js 34 KB runs code
- assets/gallery/index.html 2.5 KB
- assets/locales/en.json 15 KB
- assets/locales/zh-Hans.json 14 KB
- assets/reference-images/chibi/0054_rice_identity_comic_rendered_isolated.webp 105 KB
- assets/reference-images/chibi/0057_patting_full_belly_rendered_isolated.webp 87 KB
- assets/reference-images/chibi/0067_angry_you_are_silly_reply_rendered_isolated.webp 109 KB
- assets/reference-images/compact/0080_lounging_on_chair_rendered_isolated.webp 123 KB
- assets/reference-images/compact/0102_intimate_relationship_question_rendered_isolated.webp 93 KB
- assets/reference-images/compact/04_light_turn.webp 95 KB
- assets/reference-images/semi-chibi/0015_data_still_in_brain_rendered_isolated.webp 105 KB
- assets/reference-images/semi-chibi/0076_sitting_ready_on_chair_rendered_isolated.webp 96 KB
- assets/reference-images/semi-chibi/neutral_standing_front_isolated.webp 94 KB
- assets/reference-images/standard/01_gentle_wave.webp 101 KB
- assets/reference-images/standard/03_light_turning_step.webp 83 KB
- assets/reference-images/standard/05_side_reclining_pose.webp 90 KB
- assets/reference-images/super-deformed/0019_literal_love_reply_rendered_isolated.webp 82 KB
- assets/reference-images/super-deformed/0040_kicked_from_chair_rendered_isolated.webp 96 KB
- assets/reference-images/super-deformed/0081_stranded_on_floor_rendered_isolated.webp 70 KB
- references/assignment-schema.md 15 KB
- references/character-spec.md 4.8 KB
- references/form-profiles.md 3.8 KB
- references/gallery.md 4.5 KB
- references/language-policy.md 6.0 KB
- references/proposal-selection.md 7.1 KB
- references/provider-routing.md 14 KB
- references/qa-rubric.md 9.5 KB
- references/reference-catalog.json 5.3 KB
- references/reference-index.md 4.1 KB
- scripts/detect-language.py 7.9 KB runs code
- scripts/export-gallery.py 20 KB runs code
- scripts/generate-codex.py 17 KB runs code
- scripts/generate-nanobanana.py 13 KB runs code
- scripts/generate-openai.py 15 KB runs code
- scripts/generate-seedream.py 13 KB runs code
- scripts/language_policy.py 5.9 KB runs code
- scripts/manage-run.py 121 KB runs code
- scripts/measure-form.py 10 KB runs code
- scripts/validate-image.py 7.8 KB runs code
- tests/helpers.py 11 KB runs code
- tests/test_adapters.py 5.4 KB runs code
- tests/test_execution.py 3.1 KB runs code
- tests/test_gallery_lifecycle.py 1.1 KB runs code
- tests/test_gallery.py 14 KB runs code
- tests/test_language.py 6.9 KB runs code
- tests/test_manage_run.py 13 KB runs code
- tests/test_selection_contract.py 7.5 KB runs code
- tests/test_validate_image.py 1.6 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.
- 13d ago Changed · +6 lines · -10 tokens per session 14140e18f4fd
- 1mo ago First seen · 88 lines · 70 tokens per session scan A a8a5be3cd471
whalechan-image-character is a skill published in the GitHub repository Neko3000/deepseek-whalechan (489 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 2,425 once invoked, about $0.0002 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 skills, from other repositories
gemini-api-dev
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, video generation, speech generation (TTS), voice design, voice replication, streaming responses, background research tasks, function calling, structured output, or migrating from…
gemini-omni-flash-api
Use this skill for generative video editing, text-to-video, image-referenced video generation, first-frame-to-video, first-and-last-frame transitions, and video extensions using Gemini Omni 1.1 Flash (gemini-omni-1.1-flash) via the official google-genai SDK. Includes workflows for pre-processing/optimizing…
gemini-live-api-dev
Use this skill when building real-time, bidirectional streaming applications with the Gemini Live API, or migrating legacy Live models (2.0/2.5/3.1) to Gemini 3.8 Live. Covers WebSocket-based audio/video/text streaming, voice activity detection (VAD), background reasoning (extended thinking), asynchronous function…
gemini-watermark-remover
Remove visible Gemini image watermarks from local image files by calling the project's CLI. Use when the user wants an agent to clean one or more local Gemini-generated images and save de-watermarked output files.
aif-ai-multimodal
Analyze and generate image, audio, video and document content, falling back from native vision to the Multix CLI and live provider catalogs.
skillctx-ify
Migrate a skill to use skillctx. Identifies hardcoded values, extracts them as skill variables to /.config/skillctx/config.json, embeds a resolver script, and rewrites the skill. Invoke with the target skill name as argument.