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 closedloop-ai/claude-plugins --skill toon-formatgit clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWrote 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/closedloop-ai/claude-plugins/toon-format)<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/toon-format"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/toon-format/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/closedloop-ai/claude-plugins/toon-format"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/toon-format.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 | $0.00066 | $0.00685 |
| Opus 5 | $0.00033 | $0.00342 |
| Sonnet 5 | $0.00013 | $0.00137 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
toon-format 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TOON Format (Token-Oriented Object Notation)
TOON is a compact, human-readable encoding of the JSON data model optimized for LLM prompts. It achieves ~40% token reduction compared to JSON while maintaining lossless round-trip compatibility.
Core Syntax Rules
Array Declaration
Arrays use bracketed headers with mandatory length count:
tags[3]: admin,ops,dev
Tabular Arrays (Uniform Object Arrays)
For arrays of objects with identical structure, use field headers in braces:
patterns[2]{id,category,summary}:
P-001,pattern,"Use tokens for colors"
P-002,mistake,"Check auth before routes"
- Field names declared once in
{...}after the count - Each row contains values in declared field order
- Rows indented with 2 spaces (NEVER tabs)
Objects
Objects use indentation-based nesting (2 spaces per level):
user:
id: 123
name: Ada
Quoting Rules (Critical)
Strings MUST be quoted if they contain:
- The active delimiter (comma by default)
- Empty string, leading/trailing whitespace
- Reserved literals (
true,false,null) - Numeric-like patterns
- Colons, quotes, backslashes, brackets, braces
- Control characters or leading hyphens
Escape sequences: \\, \", \n, \r, \t
org-patterns.toon Format
Standard format for ClosedLoop organization learnings:
patterns[N]{id,category,summary,confidence,seen_count,success_rate,flags,applies_to,context,repo}:
P-001,pattern,"Summary here",high,5,0.85,,implementation-subagent,UI|styling,*
P-002,mistake,"Check auth before routes",medium,3,0.60,[REVIEW],*,auth|routes,astoria-frontend
Field notes:
summary- Always quoted (contains natural language with commas)flags-[REVIEW],[STALE],[UNTESTED],[PRUNE], or emptyapplies_to- Pipe-separated agent names or*for allcontext- Pipe-separated tagsrepo- Repository name (derived from git remote basename) or*for all repos
Validation Checklist
What ships with it
1 file 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.
- yesterday First seen · 86 lines · 66 tokens per session scan A 311019cc855c
toon-format is a skill published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 2d ago), licensed Apache-2.0. It adds 66 tokens to every session and 685 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 2026-09-07.
Other skills, from other repositories
mcp-tool-developer
Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing.
prompt-engineering
Expert prompt engineering guidance with proven techniques and anti-patterns. Invoke this skill whenever writing, editing, reviewing, or refining any prompt that will be interpreted by an AI model — system prompts, agent instructions, tool-use prompts, command templates, multi-step task prompts, or agentic workflows.…
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
nemo-curator
Curate LLM training data: dedupe, filter, PII redaction.
llava
Vision-language chat: VQA, captioning, image dialogue.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.