A setup and version-management skill for the Freshworks Development Kit, the command-line toolkit used to build Freshworks Platform 3.0 apps. It installs and switches the required FDK and Node.js versions through nvm, a Node version manager.

Use it to install, upgrade, downgrade, remove, troubleshoot, or select Freshworks FDK versions. It also supports writing a project .nvmrc file when requested.

It helps keep the development tools on compatible versions and checks that installations continue to work in new terminal sessions.

fw-setup — Skill by freshworks-developers

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 skills/freshworks-developers/fw-dev-tools/fw-setup

Any agent

npx skills add freshworks-developers/fw-dev-tools --skill fw-setup

Clone the repo

git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools

Made for: Claude Code, Codex.

Or install fw-setup, the plugin that ships this one along with the rest of its 1 skill, 7 commands.

Per session 160 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,986 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 4 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.

Model	Per session	Once invoked
Fable 5	$0.00160	$0.06986
Opus 5	$0.00080	$0.03493
Sonnet 5	$0.00032	$0.01397
Haiku 4.5	$0.00016	$0.00699

Measured 2d ago against content hash 7ee3d273ded2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

fw-setup scanned grade D with 4 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.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/detect-install-method.sh, scripts/fw-setup-quick-detect.sh, scripts/fw-setup-run-background.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **Use nvm ALWAYS** - NEVER install Node globally, NEVER use `sudo npm`

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

**Post-install MCP (optional):** After successful install/upgrade only — offer Marketplace MCP setup; **Cursor** config shape: [`references/templates/cursor-mcp-config.json`](references/templates/cursor-mcp-config.json);

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| `~/.fdk` persists after uninstall | MEDIUM | Manual removal: `rm -rf ~/.fdk` |

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Pinned 10.x.y / 9.x.y:** CDN `https://cdn.freshdev.io/fdk/vX.Y.Z.tgz` (verify **HTTP 200** with `curl` before `npm install -g`).

skills/fw-setup/SKILL.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FDK Setup

MOST IMPORTANT - ZERO TOLERANCE: FDK installation is NEVER complete until verification shows FDK accessible globally AND persists across new shells. NEVER say "installation complete" with ANY verification failures.

MANDATORY ENFORCEMENT: Verify every mutating operation (install, upgrade, downgrade, uninstall, and /fw-setup-troubleshoot --fix) with actual shell tests. /fw-setup-status, /fw-setup-troubleshoot (no --fix), and /fw-setup-use are non-Task flows (/fw-setup-use may only add .nvmrc when the user asked for --write-nvmrc). Keep iterating until verification passes. No exceptions.

You are a Freshworks FDK installation and version management enforcement layer.

Progressive disclosure: Canonical FDK / Node / Platform pins live in docs/engine-matrix.md (single source of truth—load when version truth is disputed). For per-project Node / FDK stack switching, use commands/fw-setup-use.md first, then references/macos.md / references/cross-scenarios.md for .nvmrc patterns. For complex multi-Node scenarios, PATH conflicts, or OS-specific installation issues, load references/cross-scenarios.md. For macOS-specific issues, load references/macos.md. For Windows-specific issues, load references/windows.md (PowerShell 5.1 &&, where vs where.exe, PATH refresh after nvm use). For fdk: command not found errors, load references/error-command-not-found.md. For interactive manual troubleshooting when automated --fix fails, load references/interactive-troubleshooting-guide.md and follow the step-by-step SOP protocol (ONE command at a time, wait for human output, adapt based on results). For non-blocking local fdk run, execute scripts/fw-setup-run-background.sh from the app root (shell script, not a slash command); use scripts/fw-setup-stop-shell-tasks.sh to signal matching fdk run / fdk tunnel processes.

Routing

Parse user request and execute the appropriate operation:

Read the full file on GitHub · 372 lines

Files

What ships with it

30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2d ago First seen · 372 lines · 160 tokens per session scan D 7ee3d273ded2

Subscribe to this mod's changes

fw-setup is a skill published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It adds 160 tokens to every session and 6,986 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it D with 4 findings (asks for root, reads mcp configuration, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agentic-ai agentic-workflow agentskills skills

battle-tested-engineer

Engineering judgment for code write/refactor/test and frontend UI. Trigger on code review, legacy cleanup, tests, UI with data, bloat/over-engineer complaints — even with no explicit mention, before any diff/rewrite/test suite. Output ultra-terse caveman style; code, commits, PR desc, security warnings stay normal…

sayeed1999/agent-skills · 74 tokens

agent-error-recovery

Use this skill when implementing error handling for AI agents. Activate when the user needs agents to handle failures gracefully, implement retry strategies, design fault-tolerant agent systems, or build agents that can recover from errors without human intervention.

latestaiagents/agent-skills · 53 tokens

agent-checkpointing

Implement checkpointing for agent recovery, debugging, and replay. Use this skill when building recoverable agents, implementing replay, debugging agent failures, or creating resumable workflows. Activate when: agent checkpoint, agent recovery, resume agent, agent restart, workflow replay, agent debugging, failure…

latestaiagents/agent-skills · 67 tokens

durable-state-patterns

Implement persistent agent state that survives failures and restarts. Use this skill when building stateful agents, implementing checkpointing, persisting agent memory across sessions, or recovering from failures. Activate when: durable state, agent persistence, checkpointing, agent recovery, stateful agents, state…

latestaiagents/agent-skills · 71 tokens

langgraph-workflows

Build agent workflows with LangGraph 1.0 state machines and graph patterns. Use this skill when creating agent graphs, implementing state machines, building multi-step agent workflows, or using LangGraph. Activate when: LangGraph, agent graph, state graph, agent workflow, graph nodes, conditional edges, agent state…

latestaiagents/agent-skills · 73 tokens

a2a-protocols

Implement Agent-to-Agent (A2A) communication for cross-framework interoperability. Use this skill when building multi-agent communication, implementing agent protocols, connecting agents across frameworks, or standardizing agent interfaces. Activate when: agent to agent, A2A, agent communication, agent protocol…

latestaiagents/agent-skills · 75 tokens

fw-setup