ai-actions-test-data

A test-data rule for Freshworks AI Actions, which are server-side functions that an AI feature can call. It requires one JSON example file for every action listed in actions.json.

In plain words
What is it for?
Use it when creating or checking action test fixtures. The files provide valid parameter values that load in the FDK test page, where you can edit and simulate an action.
Why use it?
It prevents actions from lacking the sample input needed for testing. Missing files or the test-data folder are treated as blocking problems.

Cursor rule

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-test-data
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 291 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 $0.00000 $0.00291
Opus 5 $0.00000 $0.00146
Sonnet 5 $0.00000 $0.00058
Haiku 4.5 $0.00000 $0.00029

Measured 2d ago against content hash bf3dcaf0aa7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-actions-test-data 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.

skills/fw-ai-actions-app/rules/ai-actions-test-data.mdc · 44 lines

What it actually says

AI Actions Test Data

Each action defined in actions.json must have a corresponding server/test_data/<functionName>.json test fixture. A missing server/test_data/ directory or any missing fixture is a blocking issue.

Location

server/test_data/actionName.json — one file per action, filename matches function name.

Structure

JSON object with keys matching parameter names from actions.json:

{
  "resource_id": "sample-123"
}
{
  "name": "Sample Resource",
  "description": "Test description"
}

Rules

  • Keys must match parameters.properties in actions.json
  • Use valid sample values for the API
  • Include all required parameters
  • Optional params can be omitted or included

Usage

  1. Create server/test_data/ directory
  2. Add actionName.json for each action
  3. Run fdk run → Open https://localhost:10001/web/test
  4. Select action → payload loads from test file → Edit if needed → Simulate
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 · 44 lines · 0 tokens per session scan A bf3dcaf0aa7b

Subscribe to this mod's changes

ai-actions-test-data is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 291 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.