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/jiaxiaojunqaq/skillject/marimo-developmentnpx skills add jiaxiaojunQAQ/SkillJect --skill marimo-developmentgit clone --depth 1 https://github.com/jiaxiaojunQAQ/SkillJectWhat 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 | $0.00097 | $0.01452 |
| Opus 5 | $0.00048 | $0.00726 |
| Sonnet 5 | $0.00019 | $0.00290 |
| Haiku 4.5 | $0.00010 | $0.00145 |
Grade A, and why
marimo-development 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 3d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- references/api/app.md 133 B
- references/api/caching.md 12 KB
- references/api/cell.md 24 B
- references/api/cli_args.md 1.9 KB
- references/api/control_flow.md 636 B
- references/api/diagrams.md 307 B
- references/api/html.md 115 B
- references/api/index.md 2.1 KB
- references/api/inputs/anywidget.md 3.4 KB
- references/api/inputs/array.md 294 B
- references/api/inputs/batch.md 334 B
- references/api/inputs/button.md 269 B
- references/api/inputs/chat.md 8.8 KB
- references/api/inputs/checkbox.md 249 B
- references/api/inputs/code_editor.md 109 B
- references/api/inputs/data_editor.md 126 B
- references/api/inputs/data_explorer.md 1.5 KB
- references/api/inputs/dataframe.md 1.5 KB
- references/api/inputs/dates.md 877 B
- references/api/inputs/dictionary.md 556 B
- references/api/inputs/dropdown.md 655 B
- references/api/inputs/file_browser.md 166 B
- references/api/inputs/file.md 583 B
- references/api/inputs/form.md 255 B
- references/api/inputs/index.md 2.7 KB
- references/api/inputs/microphone.md 252 B
- references/api/inputs/multiselect.md 311 B
- references/api/inputs/nav_menu.md 1.1 KB
- references/api/inputs/number.md 253 B
- references/api/inputs/radio.md 275 B
- references/api/inputs/range_slider.md 312 B
- references/api/inputs/refresh.md 273 B
- references/api/inputs/run_button.md 106 B
- references/api/inputs/slider.md 614 B
- references/api/inputs/switch.md 243 B
- references/api/inputs/table.md 1.5 KB
- references/api/inputs/tabs.md 119 B
- references/api/inputs/text_area.md 103 B
- references/api/inputs/text.md 248 B
- references/api/layouts/accordion.md 137 B
- references/api/layouts/callout.md 452 B
- references/api/layouts/carousel.md 350 B
- references/api/layouts/index.md 1.7 KB
- references/api/layouts/json.md 204 B
- references/api/layouts/justify.md 64 B
- references/api/layouts/lazy.md 366 B
- references/api/layouts/outline.md 253 B
- references/api/layouts/plain.md 26 B
- references/api/layouts/routes.md 950 B
- references/api/layouts/sidebar.md 704 B
- references/api/layouts/stacks.md 1.4 KB
- references/api/layouts/stat.md 648 B
- references/api/layouts/tree.md 232 B
- references/api/markdown.md 1.6 KB
- references/api/media/audio.md 232 B
- references/api/media/download.md 103 B
- references/api/media/image_compare.md 387 B
- references/api/media/image.md 266 B
- references/api/media/index.md 607 B
- references/api/media/pdf.md 22 B
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.
- 3d ago First seen · 201 lines · 97 tokens per session scan A 54174d07d685
marimo-development is a skill published in the GitHub repository jiaxiaojunQAQ/SkillJect (77 stars, last pushed 2mo ago), with no licence file. It adds 97 tokens to every session and 1,452 once invoked, about $0.0005 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
dali-dynamic-mode
DALI imperative dynamic mode (nvidia.dali.experimental.dynamic, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.
datachain-core
Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. If the request mentions creating, saving, listing, exploring datasets or buckets, use datachain-knowledge instead.
mflux-model-porting
Port ML models into mflux/MLX with correctness-first validation, then refactor toward mflux style.
minicpm5-finetune-trl
Fine-tune MiniCPM5-1B with bare-metal TRL + PEFT, including assistant-only loss via a chat-template patch. Use when the user wants minimal Python, no YAML, full control, or asks for "TRL", "SFTTrainer", "PEFT", "LoraConfig", "assistantonlyloss".
minicpm5-finetune-unsloth
Fine-tune MiniCPM5-1B with unsloth for tight-VRAM single-GPU LoRA / QLoRA. Use when the user wants "unsloth", "FastLanguageModel", QLoRA on a 24 GB consumer GPU, or asks for the smallest VRAM footprint.
minicpm5-deploy-transformers
Run MiniCPM5-1B with Hugging Face Transformers for one-shot Python generation on GPU (bfloat16) or CPU (float32). Use when the user wants a quick Python script, no server, no extra deps, or asks for "Transformers", "AutoModelForCausalLM", "model.generate" with MiniCPM5.