validation-workflow

A validation and repair workflow for Freshworks Platform 3.0 apps. It runs the Freshworks Development Kit's validation command after files are created and repeatedly fixes platform or code-style errors.

In plain words
What is it for?
Use it when creating or editing Freshworks apps to validate the manifest and source files, check the Node.js and FDK versions, and apply fixes through several validation rounds.
Why use it?
It catches app problems during development and requires validation errors to be resolved before the app is treated as finished.

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/validation-workflow
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools
Per session 2,338 This file is loaded in full into every session.
When invoked 2,338 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 $0.02338 $0.02338
Opus 5 $0.01169 $0.01169
Sonnet 5 $0.00468 $0.00468
Haiku 4.5 $0.00234 $0.00234

Measured yesterday against content hash f53bc2738dbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validation-workflow 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 yesterday.

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-app-dev/rules/validation-workflow.mdc · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validation & Auto-Fix Workflow

🚨 ZERO TOLERANCE: App is NEVER complete until ALL errors (platform AND lint) are fixed.

FDK / Node are not installed by fw-app-dev. This rule file and fw-app-dev edit app code and run fdk validate when the CLI exists; they do not install fdk, switch Node majors, or fix PATH / nvm. For that, use the fw-setup skill when present (/fw-setup-install, /fw-setup-upgrade, /fw-setup-use, /fw-setup-status). If fw-setup is missing, tell the user to add it (npx @freshworks/fw-dev-tools install). Canonical text: SKILL.mdFDK / Node.js toolchain — not provided by fw-app-dev.

REQUIRED FOR NEW APPS: FDK 10.0.1 + Node.js 24.x ("engines": { "node": "24.11.0", "fdk": "10.0.1" }). If fdk validate cannot start, use fw-setup first. LAST RESORT engines downgrade to FDK 9.8.2 + Node 18.20.8 is only after six validate+fix iterations or CLI cannot run on 10.0.1+24.11.0 under the conditions in SKILL.md (top section).

Before the first fdk validate: run the Manifest + toolchain gate in SKILL.md (node/fdk vs manifest.jsonfw-setup / /fdk-migrate / align engines up). Never downgrade the shell or manifest to FDK 9 / Node 18 to silence engines mismatch when FDK 10 + Node 24 is installed.

Mandatory Workflow

Step 0: Gate (before any fdk validate)

Read manifest.json and compare to node --version / fdk version. Follow SKILL.mdManifest + toolchain gate before any fdk validate. Do not skip for /fdk-fix, /fdk-refactor, or generation workflows. (For structured pre-submission review, use fw-review skill.)

Step 1: Automatic Validation After File Creation

AFTER creating ALL app files, AUTOMATICALLY run:

cd <app-directory>
fdk validate

DO NOT ask user to run it manually.

If the command fails before normal app validation, follow SKILL.md: fw-setup first; /fdk-migrate when platform-version is not 3.0; LAST RESORT downgrade only when that section’s bullets are satisfied (never as a substitute for migrate/setup).

Read the full file on GitHub · 280 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. yesterday First seen · 280 lines · 2,338 tokens per session scan A f53bc2738dbc

Subscribe to this mod's changes

validation-workflow is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 7d ago), licensed MIT. It adds 2,338 tokens to every session, about $0.0117 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.