ai-actions-schemas

ai-actions-schemas is a cursor rule for Cursor from freshworks-developers/fw-dev-tools. It costs 0 tokens per session (1,188 once invoked), scanned A, original, MIT.

A set of rules for defining AI action inputs and outputs in an actions.json file using JSON Schema, a standard format for describing valid data.

In plain words
What is it for?
Use it when creating AI action schemas with fields such as strings, numbers, required values, fixed choices, regular-expression patterns, or email and date-time formats.
Why use it?
It helps action parameters and responses stay predictable, clearly documented, and restricted to acceptable values or formats.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

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/freshworks-developers/fw-dev-tools/ai-actions-schemas
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools

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 ai-actions-schemas

README.md
[![agentmods](https://agentmods.dev/badge/rules/freshworks-developers/fw-dev-tools/ai-actions-schemas.svg)](https://agentmods.dev/rules/freshworks-developers/fw-dev-tools/ai-actions-schemas)
Your own site
<a href="https://agentmods.dev/rules/freshworks-developers/fw-dev-tools/ai-actions-schemas"><img src="https://agentmods.dev/badge/rules/freshworks-developers/fw-dev-tools/ai-actions-schemas.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 1,188 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 $0.00000 $0.01188
Opus 5 $0.00000 $0.00594
Sonnet 5 $0.00000 $0.00238
Haiku 4.5 $0.00000 $0.00119

Measured 6d ago against content hash 91f675b808cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ai-actions-schemas 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 6d 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.

skills/fw-ai-actions-app/rules/ai-actions-schemas.mdc · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Actions Schemas (actions.json)

Structure

Each action in actions.json has:

  • display_name — Human-readable name
  • description — What the action does
  • parameters — JSON Schema for input (request)
  • response — JSON Schema for output

Parameters Schema

Preferred: Flat Structure

  • Types: string, number, integer, boolean
  • All properties need description
  • Use required array for mandatory fields
  • Use $schema: "http://json-schema.org/draft-07/schema#"
  • Draft-07 keywords on string (and similar) properties are allowed where the automation UI supports them—common ones: enum (fixed allowed values), pattern (regex), format (semantic hint, e.g. email, date-time)

String constraints (enum, pattern, format)

{
  "parameters": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "priority": {
        "type": "string",
        "enum": ["low", "medium", "high", "urgent"],
        "description": "Ticket priority"
      },
      "order_id": {
        "type": "string",
        "pattern": "^[A-Z]{2}-[0-9]{6}$",
        "description": "Vendor order id, e.g. OR-000123"
      },
      "notify_email": {
        "type": "string",
        "format": "email",
        "description": "Email to notify when the action completes"
      }
    },
    "required": ["priority", "order_id"]
  }
}

Arrays of Primitives Allowed

{
  "parameters": {
    "properties": {
      "ids": {
        "type": "array",
        "items": { "type": "string" },
        "description": "List of resource IDs"
      },
      "tags": {
        "type": "array",
        "items": { "type": "string" },
        "description": "Tags to apply"
      }
    }
  }
}

Nested Objects: Flatten or Construct in server.js

If API requires nested object, accept flat params and build in server.js:

{ "name": { "type": "string" }, "email": { "type": "string" } }
// server.js builds: { contact: { name, email } }

Read the full file on GitHub · 159 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. 6d ago First seen · 159 lines · 0 tokens per session scan A 91f675b808cb

Subscribe to this mod's changes

ai-actions-schemas is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,188 tokens. 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.