toon-responses

toon-responses is a cursor rule for Cursor from titanzero/outlook-mcp. It costs 0 tokens per session (504 once invoked), scanned A, original, from a forked repository, MIT.

A set of rules for formatting coding-agent responses in TOON, a compact notation for structured data. It requires data handlers to provide both structured output and readable plain text.

In plain words
What is it for?
Formatting email lists, search results, single records, and other handler responses through shared response-formatting helpers.
Why use it?
It keeps responses usable in both machine-readable and human-readable forms. It also gives list and detail responses consistent data shapes.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

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 rules/titanzero/outlook-mcp/toon-responses
Clone the repo
git clone --depth 1 https://github.com/titanzero/outlook-mcp

Made for: Cursor.

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 toon-responses

README.md
[![agentmods](https://agentmods.dev/badge/rules/titanzero/outlook-mcp/toon-responses.svg)](https://agentmods.dev/rules/titanzero/outlook-mcp/toon-responses)
Your own site
<a href="https://agentmods.dev/rules/titanzero/outlook-mcp/toon-responses"><img src="https://agentmods.dev/badge/rules/titanzero/outlook-mcp/toon-responses.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin fork From a forked repository.
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 $0.00000 $0.00504
Opus 5 $0.00000 $0.00252
Sonnet 5 $0.00000 $0.00101
Haiku 4.5 $0.00000 $0.00050

Measured 5d ago against content hash 3aaa5bbf62ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

toon-responses 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.

.cursor/rules/toon-responses.mdc · 64 lines

What it actually says

TOON Response Formatting

Purpose

TOON (Token-Oriented Object Notation) is the compact response mode controlled by config.RESPONSE_FORMAT / OUTLOOK_RESPONSE_FORMAT.

Handler Pattern

Each data-returning handler should provide both a structured payload and a text fallback, then call formatResponse():

const { formatResponse } = require('../utils/response-formatter');
const { makeResponse } = require('../utils/response-helpers');

const structured = { emails: rows };
const textFallback = `Found ${rows.length} emails:\n...`;

const text = formatResponse(structured, textFallback);
return makeResponse(text);

Data Shape Guidance

Tabular (arrays of uniform objects)

Use for list/search outputs where each row has the same shape:

{ emails: [
  { n: 1, unread: true, date: '...', from: '...', subject: '...', id: '...' },
  { n: 2, unread: false, date: '...', from: '...', subject: '...', id: '...' },
]}

TOON compresses this efficiently with a shared header.

Key-Value (single objects)

Use for detail responses (read-email, single event):

{ from: '...', to: '...', subject: '...', date: '...', body: '...' }

TOON-Specific Rules

  1. Always provide both structured data and text fallback.
  2. Keep structured output flat when possible; avoid deep nesting.
  3. Keep ISO dates/times in structured data.
  4. Format dates for readability only in the text fallback.

Formatter API (utils/response-formatter.js)

  • formatResponse(structuredData, textFallback) — returns TOON or text based on config
  • formatAsToon(data) — always returns TOON string
  • isToonEnabled() — boolean check

Config and Tests

  • Default mode is 'toon'.
  • Set OUTLOOK_RESPONSE_FORMAT=text to force plain text.
  • In tests, set process.env.OUTLOOK_RESPONSE_FORMAT = 'text' before module imports.
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 · 64 lines · 0 tokens per session scan A 3aaa5bbf62ac

Subscribe to this mod's changes

toon-responses is a cursor rule published in the GitHub repository titanzero/outlook-mcp (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 504 tokens. A static security scan graded it A with 0 findings. It comes from a forked repository.