ai-actions-validation

A set of rules for validating AI Actions apps with the fdk command-line tool. It requires checking the app files and fixing blocking errors after creation.

In plain words
What is it for?
Use it after creating or changing an AI Actions app to run validation, fix fatal problems within the stated limit, and report the result.
Why use it?
It catches invalid manifests, missing files, mismatched function names, and other errors that can prevent an app from working.

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-validation
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 655 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 $0.00655
Opus 5 $0.00000 $0.00328
Sonnet 5 $0.00000 $0.00131
Haiku 4.5 $0.00000 $0.00065

Measured 2d ago against content hash 00057804748f, 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-validation 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-validation.mdc · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Actions Validation & Autofix

CRITICAL: After creating ALL app files, run fdk validate automatically and fix fatal errors.

Before fdk validate: follow ../../fw-app-dev/SKILL.md (Manifest + toolchain gate) in this order: fw-setup if Node/FDK is missing or wrong → /fdk-migrate for legacy 2.x or old engines → validate. Never downgrade shell or manifest engines to 9.x / 18 as a shortcut (except LAST RESORT in fw-app-dev SKILL.md when only the toolchain blocks validation).

Mandatory Post-Creation Process

Step 1: Run fdk validate

cd <app-directory>
fdk validate

Step 2: Fix Fatal Errors Only (2 iterations)

FIX: JSON errors, missing files, manifest structure, request template errors, function name mismatch IGNORE: Lint warnings, code style suggestions

Step 3: Present Results

  • If passes: "✅ AI Actions app generated and validated successfully!"
  • If fails: List only FATAL errors with fix directions

Validation Checklist

manifest.json

  • platform-version: "3.0"
  • modules.common.requests declares all request templates
  • modules.common.functions declares all action functions with timeout
  • At least one product module (support_ticket, chat_conversation, etc.)
  • engines block with node and fdk

actions.json

  • Function names match server.js exactly
  • $schema in parameters and response
  • All properties have descriptions
  • required array for mandatory params

config/requests.json

  • Host is FQDN only (no path)
  • Path starts with /
  • Uses <%= %> not {{}}
  • Single top-level JSON object

server.js

  • Uses $request.invokeTemplate() not .post/.get
  • Uses renderData(null, data) for success
  • Uses renderData(error, null) for errors
  • Function names match actions.json

test_data

  • server/test_data/ directory exists (missing = blocking issue)
  • One JSON file per action: server/test_data/actionName.json (missing fixture = blocking issue)
  • Keys match parameter names
  • Valid sample values

Read the full file on GitHub · 66 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 · 66 lines · 0 tokens per session scan A 00057804748f

Subscribe to this mod's changes

ai-actions-validation 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 655 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.