CTON

CTON is a command for Claude Code from danielsimonjr/memory-mcp. It costs 11 tokens per session (328 once invoked), scanned A, original, MIT.

A command that compresses files into CTON, a compact text format intended to use less space in an AI agent’s working context. It supports common formats such as JSON, YAML, Markdown, CSV, code, XML, and HTML.

In plain words
What is it for?
Use it to compress one file, process directories recursively, choose a compression level, batch-process files, or decompress a CTON file.
Why use it?
It helps fit large files or groups of files into limited context space while keeping them available for agent work. Compressed files can also be restored to their original form.

Command for Claude Code

Part of the memory-mcp plugin — 1 skill, 9 commands, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add commands/danielsimonjr/memory-mcp/cton
Clone the repo
git clone --depth 1 https://github.com/danielsimonjr/memory-mcp

Made for: Claude Code.

Or install memory-mcp, the plugin that ships this one along with the rest of its 1 skill, 9 commands, 1 MCP server.

Wrote 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.

agentmods badge for CTON

README.md
[![agentmods](https://agentmods.dev/badge/commands/danielsimonjr/memory-mcp/cton.svg)](https://agentmods.dev/commands/danielsimonjr/memory-mcp/cton)
Your own site
<a href="https://agentmods.dev/commands/danielsimonjr/memory-mcp/cton"><img src="https://agentmods.dev/badge/commands/danielsimonjr/memory-mcp/cton.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 328 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.00328
Opus 5 $0.00005 $0.00164
Sonnet 5 $0.00002 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured 5d ago against content hash 2906bd9a8b12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

CTON 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 5d 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.

.claude/commands/CTON.md · 37 lines

What it actually says

Compress for Context (CTON)

Run the compress-for-context tool to compress files using CTON (Compact Token-Oriented Notation) format, optimized for LLM context windows.

Instructions

  1. Run the compression tool on the specified file(s):
C:\mcp-servers\memory-mcp\tools\compress-for-context\compress-for-context.exe $ARGUMENTS
  1. The tool supports multiple formats: JSON, YAML, Markdown, CSV/TSV, Text/Log, TypeScript/JavaScript, XML/HTML.

  2. Report the compression results and token savings.

Common Options

  • -o, --output <path> - Output file path
  • -l, --level <level> - Compression level: light, medium, aggressive
  • -b, --batch - Batch mode for multiple files
  • -r, --recursive - Process directories recursively
  • -d, --decompress - Decompress a CTON file

Usage Examples

  • /project:CTON package.json - Compress a single JSON file
  • /project:CTON ./src -b -r - Batch compress all files in src/
  • /project:CTON data.cton -d - Decompress a CTON file
  • /project:CTON large-file.md -l aggressive - Aggressive compression
Changes

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.

  1. 5d ago First seen · 37 lines · 11 tokens per session scan A 2906bd9a8b12

Subscribe to this mod's changes

CTON is a command published in the GitHub repository danielsimonjr/memory-mcp (3 stars, last pushed 2d ago), licensed MIT. It adds 11 tokens to every session and 328 once invoked, about $0.0001 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 2026-08-31.