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 georgekhananaev/claude-skills-vault --skill toongit clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultWrote 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/georgekhananaev/claude-skills-vault/toon)<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/toon"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/toon/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/georgekhananaev/claude-skills-vault/toon"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/toon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.01692 |
| Opus 5 | $0.00022 | $0.00846 |
| Sonnet 5 | $0.00009 | $0.00338 |
| Haiku 4.5 | $0.00004 | $0.00169 |
Grade A, and why
toon 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 12d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- toon — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TOON Format Guide
Overview
TOON (Token-Oriented Object Notation) is a compact encoding of JSON designed for LLM input. Combines YAML-style indentation w/ CSV-style tables for uniform arrays.
Key benefits:
- ~40% fewer tokens vs JSON
- 73.9% accuracy vs 69.7% for JSON in retrieval tasks
- Explicit length declarations for validation
- Lossless JSON round-trips
Syntax
Objects (YAML-style indentation)
user:
name: John
age: 30
address:
city: NYC
zip: 10001
Uniform Arrays (Tabular)
users[3]{id,name,email}:
1,John,[email protected]
2,Jane,[email protected]
3,Bob,[email protected]
[N]= array length (req for validation){fields}= column schema (declared once)
Scalar Arrays
tags[4]: api,rest,json,toon
Non-uniform Arrays (Nested)
items:
- id: 1
type: book
meta:
pages: 200
- id: 2
type: video
meta:
duration: 3600
Conversion Rules
JSON to TOON
- Objects => indented key-value pairs
- Uniform arrays => tabular
[N]{fields}:format - Mixed/nested arrays =>
-list notation - Scalars => quote only when containing
,or special chars
Examples
JSON:
{"orders":[{"id":1,"item":"Book","qty":2,"price":29.99},{"id":2,"item":"Pen","qty":10,"price":1.99}]}
TOON:
orders[2]{id,item,qty,price}:
1,Book,2,29.99
2,Pen,10,1.99
Nested JSON:
{"config":{"db":{"host":"localhost","port":5432},"cache":{"enabled":true,"ttl":300}}}
TOON:
config:
db:
host: localhost
port: 5432
cache:
enabled: true
ttl: 300
When to Use TOON
TOON replaces data serialization formats when sending to LLMs.
Formats to convert → TOON:
| Format | Convert? | Notes |
|---|---|---|
| JSON | Yes | Primary use case |
| JSON compact | Yes | Same as JSON |
| YAML | Yes | Structured data |
| XML | Yes | Verbose, big savings |
What ships with it
7 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.
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.
- 12d ago First seen · 251 lines · 44 tokens per session scan A 359773d5500d
toon is a skill published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 1,692 once invoked, about $0.0002 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
claude-opus-4-5-migration
A guide for moving prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. It covers model-name changes and prompt adjustments for known behavior differences.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
shap
Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature attributions, handling multi-output explanations, and producing local or global SHAP visualizations.
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
fine-tuning-expert
Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…