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.
npx agentmods add commands/freshworks-developers/fw-dev-tools/fw-setup-usegit clone --depth 1 https://github.com/freshworks-developers/fw-dev-toolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/freshworks-developers/fw-dev-tools/fw-setup-use)<a href="https://agentmods.dev/commands/freshworks-developers/fw-dev-tools/fw-setup-use"><img src="https://agentmods.dev/badge/commands/freshworks-developers/fw-dev-tools/fw-setup-use.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00045 | $0.04214 |
| Opus 5 | $0.00023 | $0.02107 |
| Sonnet 5 | $0.00009 | $0.00843 |
| Haiku 4.5 | $0.00005 | $0.00421 |
Grade A, and why
fw-setup-use 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FDK setup — use (/fw-setup-use)
/fw-setup use: align this shell (and optionally .nvmrc) with the Node + FDK stack the workspace needs.
DEFAULT BEHAVIOR (without --global): Installs FDK locally in node_modules/ for workspace-scoped use. This ensures each project has its own FDK version without affecting global installs.
WITH --global FLAG: Uses globally installed FDK (no local install).
Windows users: same slash-command experience — just run
/fw-setup-use 9in your IDE. The agent automatically uses the correct implementation (fw-setup-use.ps1) behind the scenes.
Scope:
- Without
--global:- macOS/Linux (nvm): Changes only current shell (
nvm use) - Windows (nvm-windows): Use the PowerShell implementation (
scripts/fw-setup-use.ps1) — it avoidsnvm useso the system-wide nvm-windows symlink is not flipped; it prepends the selected Node install directory to this session’sPATHand refreshesPATHfrom Machine+User (helpsfdkresolve immediately). - Homebrew/Chocolatey: System-wide already (no version switching)
- macOS/Linux (nvm): Changes only current shell (
- With
--global: Sets as default for all new shells across all environments:- nvm (macOS/Linux):
nvm alias default <version>+ updates~/.zshrcand~/.bashrcwithnvm useline - nvm-windows: Runs
nvm use+ best-effortnvm alias default(persists via nvm-windows symlink semantics) - Homebrew (macOS): System-wide already (no action needed)
- Chocolatey (Windows): System-wide already (no action needed)
- nvm (macOS/Linux):
Important Windows Note: Raw nvm use on nvm-windows flips a single system-wide symlink, which makes “workspace-only” switches look global. /fw-setup-use on Windows should prefer fw-setup-use.ps1 unless the user explicitly passed --global (then persisting via nvm use is intended).
When to use
- After
cdinto an app,fdkis missing or the wrong major → usually wrong active Node (global npm prefix). - Switching between a FDK 10.x app (any Node 24.x) and a FDK 9.x app (any Node 18.x) during migrations.
- Compatibility: Node 24.x works with any FDK 10.y; Node 18.x works with any FDK 9.y
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.
- 3d ago First seen · 289 lines · 45 tokens per session scan A 20f4fbbcab84
fw-setup-use is a command published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 9d ago), licensed MIT. It adds 45 tokens to every session and 4,214 once invoked, about $0.0002 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.
Other commands, from other repositories
business-feature-map
Generate or refresh the business feature inventory.
master-test-plan
Generate or refresh the risk-ranked master test plan.
bottleneck-detect
Analyze performance bottlenecks in swarm operations and suggest optimizations.
swarm-init
Initialize a Ruflo swarm with specified topology and configuration.
post-task
Execute post-task cleanup, performance analysis, and memory storage.
auto-topology
Automatically select the optimal swarm topology based on task complexity analysis.