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/fdk-migrategit clone --depth 1 https://github.com/freshworks-developers/fw-dev-toolsWhat 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 | $0.00102 | $0.02286 |
| Opus 5 | $0.00051 | $0.01143 |
| Sonnet 5 | $0.00020 | $0.00457 |
| Haiku 4.5 | $0.00010 | $0.00229 |
Grade A, and why
fdk-migrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FDK Migrate: Platform 2.x → 3.0
Usage: /fdk-migrate
Orchestration (matches fw-app-dev SKILL): (1) If FDK 10 + Node 24 is not installed → fw-setup first, then this migrate flow, then fdk validate. (2) If FDK 10 + Node 24 is installed and the app is legacy → this migrate flow then fdk validate. (3) If the app is already 3.0 with 24.x / 10.x engines → you do not need this command for migration; use /fdk-fix only (for structured pre-submission review, use fw-review skill). Never “fix” migration by installing FDK 9 or switching to Node 18 — that is the opposite of this command.
You are migrating a legacy Freshworks app to Platform 3.0. Typical source state:
platform-version:"2.3"(or"2.2"/"2.1"/ missing)manifest.json→engines: oftenfdk9.xandnode18.x**- Patterns:
productblock,whitelisted-domains,$request.post/.get, plain HTML controls
Target: platform-version "3.0", modules layout, request templates, Crayons, and engines "node": "24.11.0", "fdk": "10.0.1" (fw-app-dev default).
Step 0: Verify environment (upgrade off 9.x / Node 18 first)
CRITICAL: Do not use FDK 9.x on Node 18 to validate a finished Platform 3.0 app. Upgrade the machine (shell) to Node 24.x + FDK 10.x before you rely on fdk validate for the migrated tree. Platform 3.0 migration aligns with fw-app-dev: FDK 10.0.1 and Node.js 24.x (templates use Node 24.11.0, FDK 10.0.1).
Toolchain (same split as /fdk-fix, /fdk-refactor, and always-on rules/validation-workflow.mdc):
- fw-app-dev does not install
fdk, Node, nvm, or PATH. - Use
fw-setupwhen present:/fw-setup-install,/fw-setup-upgrade,/fw-setup-use,/fw-setup-status. - If fw-setup is missing: prompt the user to add it (
npx @freshworks/fw-dev-tools install), then continue Step 0. - Do not invent one-off global
npm installscripts here. Canonical wording: SKILL.md → FDK / Node.js toolchain — not provided by fw-app-dev.
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 · 128 lines · 102 tokens per session scan A bb735aeafae4
fdk-migrate is a command published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It adds 102 tokens to every session and 2,286 once invoked, about $0.0005 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
bottleneck-detect
Analyze performance bottlenecks in swarm operations and suggest optimizations.
auto-agent
Automatically route a task to the optimal agent using Q-Learning. There is no auto agent family in v3 — the closest live surface is route, backed by swarm coordinate / autopilot for full multi-agent orchestration.
github-swarm
Create a specialized swarm for GitHub repository management.
self-healing
Automatically detect and recover from errors without interrupting your flow.
swarm-init
Initialize a Ruflo swarm with specified topology and configuration.
post-edit
Execute post-edit processing including formatting, validation, and memory updates.