datoon CLAUDE.md

Repository instructions for datoon, a tool that converts suitable JSON data into TOON, a more compact format for language-model workloads. They describe which files are authoritative and which generated files mirror them.

In plain words
What is it for?
Use them when developing, testing, documenting, or maintaining the datoon JSON-to-TOON gateway and its related packages and plugins.
Why use it?
They help coding agents change the correct source files and keep the Python package, command-line tools, plugins, documentation, and generated copies consistent.

Instructions file

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 instructions/andrii-su/datoon/claude-md
Clone the repo
git clone --depth 1 https://github.com/andrii-su/datoon
Per session 1,617 This file is loaded in full into every session.
When invoked 1,617 The same file — it is already loaded in full.
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 $0.01617 $0.01617
Opus 5 $0.00809 $0.00809
Sonnet 5 $0.00323 $0.00323
Haiku 4.5 $0.00162 $0.00162

Measured 2d ago against content hash 1890e79c7fe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

datoon CLAUDE.md 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 2d 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.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - datoon

This file is the maintainer guide for agents working in this repository. It explains source-of-truth files, generated mirrors, and checks that must stay green.

Project Overview

datoon is a smart JSON-to-TOON gateway for LLM data workloads. It converts structured JSON only when the payload is a good TOON candidate and estimated token savings clear the configured threshold.

It ships as:

  • Python package under src/datoon/;
  • CLI command datoon;
  • MCP server command datoon-mcp;
  • Claude Code plugin metadata under .claude-plugin/;
  • Codex plugin under plugins/datoon/;
  • standalone skill artifact datoon.skill;
  • docs and benchmarks.

Repository Layout

datoon/
├── README.md                         # Product overview and benchmark summary
├── INSTALL.md                        # User install guide
├── CONTRIBUTING.md                   # Contributor workflow
├── CLAUDE.md                         # Maintainer guide for agents
├── SECURITY.md
├── pyproject.toml
├── uv.lock
│
├── src/datoon/                       # Python package source
│   ├── analyzer.py                   # Payload structure suitability checks
│   ├── converter.py                  # JSON normalization, TOON CLI call, policy gating
│   ├── models.py                     # Config/report/outcome dataclasses
│   ├── cli.py                        # CLI entrypoint
│   └── mcp_server.py                 # MCP server tools
│
├── skills/datoon/                    # Skill source of truth
│   ├── SKILL.md                      # LLM-facing behavior
│   └── README.md                     # Human-facing skill docs
│
├── SKILL.md                          # Mirrored skill copy
├── datoon/SKILL.md                   # Mirrored skill copy for .skill layout
├── plugins/datoon/                   # Codex plugin distribution
├── datoon.skill                      # ZIP artifact containing datoon/SKILL.md
│
├── benchmarks/
│   ├── payloads.json                 # Main benchmark payload config
│   ├── run.py                        # JSON/TOON efficiency benchmark
│   └── agent_skill_eval/             # Saved subagent evaluation artifacts
│
├── scripts/
│   ├── validate_skill_sync.py        # Mirror/archive consistency check
│   ├── ab_skill_benchmark.py         # Claude CLI A/B benchmark harness
│   └── summarize_agent_skill_eval.py # Summarizes saved subagent artifacts
│
├── tests/                            # Unit and integration tests
├── docs/                             # Static docs site
└── .github/workflows/                # CI, release, publish, skill sync

Read the full file on GitHub · 176 lines

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. 2d ago First seen · 176 lines · 1,617 tokens per session scan A 1890e79c7fe6

Subscribe to this mod's changes

datoon CLAUDE.md is an instructions file published in the GitHub repository andrii-su/datoon (2 stars, last pushed 9d ago), licensed MIT. It adds 1,617 tokens to every session, about $0.0081 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.