fdk-enforcement

Rules for installing and managing the Freshworks Development Kit, the toolkit used to build Freshworks apps. It covers setup, status checks, upgrades, downgrades, removal, troubleshooting, and Node.js version selection, but does not create apps.

In plain words
What is it for?
Use it to install, inspect, upgrade, downgrade, uninstall, troubleshoot, or select the Node.js environment for FDK.
Why use it?
It keeps FDK setup tasks separate from app development and defines the supported commands and version transitions.

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/fdk-enforcement
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools
Per session 734 This file is loaded in full into every session.
When invoked 734 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 $0.00734 $0.00734
Opus 5 $0.00367 $0.00367
Sonnet 5 $0.00147 $0.00147
Haiku 4.5 $0.00073 $0.00073

Measured 2d ago against content hash 7f17a6af4ba3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fdk-enforcement 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-setup/rules/fdk-enforcement.mdc · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FDK Setup Skill - Enforcement Rules

Scope

This skill handles FDK installation and management only. It does NOT create apps.

How This Skill Works

User must explicitly invoke commands (Confluence-style primary names):

  • /fw-setup-install (optional --version X.Y.Z for FDK 10.x.y CDN pin)
  • /fw-setup-status (optional --verbose; inline only)
  • /fw-setup-upgrade (optional --to X.Y.Z for pinned semver)
  • FDK 9 + Node 18 → FDK 10 + Node 24.11: use /fw-setup-install / /fw-setup-upgrade on an active Node 24 shell (see SKILL.md); there is no separate /fw-setup-migrate command file in this skill.
  • /fw-setup-downgrade (optional pinned 9.x.y; else latest 9 line)
  • /fw-setup-uninstall (FDK only — no --all / no nvm removal)
  • /fw-setup-troubleshoot (inline diagnose; --fix = shell Task)
  • /fw-setup-use (workspace nvm use / .nvmrc for FDK 10 vs 9 stack; optional --write-nvmrc; inline only)

Legacy aliases (same flows): /fdk-install, /fdk-status, /fdk-upgrade, /fdk-downgrade, /fdk-uninstall

What happens:

  1. User types slash command
  2. Command file under commands/fw-setup-*.md defines the Task (or inline status)
  3. Subagent spawned with full context for mutating operations
  4. Operation executes autonomously
  5. Reports back results

Important Limitation

This skill does NOT automatically check for FDK when users request app creation.

If user says "create a freshdesk app" without first running /fw-setup-install (or legacy /fdk-install), the agent may create files manually without proper FDK setup.

Before creating any Freshworks app, users should:

  1. First, install FDK: /fw-setup-install (or legacy /fdk-install)

  2. Then, optionally install fw-app-dev skill for templates, Crayons, and app-specific slash commands (those live in fw-app-dev, not fw-setup).

  3. Then proceed with app creation using fdk create where possible.

Read the full file on GitHub · 59 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 · 59 lines · 734 tokens per session scan A 7f17a6af4ba3

Subscribe to this mod's changes

fdk-enforcement is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It adds 734 tokens to every session, about $0.0037 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.