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 rules/freshworks-developers/fw-dev-tools/smart-prerequisites-checkgit 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 | $0.00019 | $0.02691 |
| Opus 5 | $0.00010 | $0.01345 |
| Sonnet 5 | $0.00004 | $0.00538 |
| Haiku 4.5 | $0.00002 | $0.00269 |
Grade C, and why
smart-prerequisites-check scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules coverage .fdk How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Prerequisites Check — Migration-Aware
CRITICAL: Run this check BEFORE generating apps, fixing errors, migrating, refactoring, or reviewing.
Check Order
- Check current toolchain (Node + FDK versions)
- Check manifest.json (platform-version + engines) if present
- Apply smart routing logic based on the combination
Step 1: Check Toolchain
node --version 2>&1
fdk version 2>&1
Parse output:
NODE_MAJOR= extract major version (24, 18, etc.)FDK_MAJOR= extract major version (10, 9, etc.)NODE_FOUND= true ifnode --versionsucceedsFDK_FOUND= true iffdk versionsucceeds
Step 2: Check Manifest (if present)
If working directory or user-specified directory contains manifest.json:
# Read manifest.json
cat manifest.json | grep -E '"platform-version"|"engines"' -A 2
Parse:
MANIFEST_PLATFORM= value ofplatform-versionfield ("2.3", "3.0", etc.)MANIFEST_FDK= value ofengines.fdkfieldMANIFEST_NODE= value ofengines.nodefield
Step 3: Smart Routing Logic
AUTOMATIC ROUTING - NO USER PROMPT: The skill automatically detects the state and takes the appropriate action. Three main scenarios:
| Scenario | Installed Toolchain | Manifest State | Automatic Action |
|---|---|---|---|
| A | FDK 9.x or not found | Platform 2.x | Upgrade toolchain → Migrate → Validate |
| B | FDK 10.x + Node 24.x | Platform 2.x | Migrate → Validate |
| C | FDK 10.x + Node 24.x | Platform 3.0 (engines match) | Validate directly |
| D | FDK 10.x + Node 24.x | Platform 3.0 (engines mismatch) | Update engines → Clean deps → Validate |
| E | FDK 9.x or not found | Platform 3.0 | Upgrade toolchain → Validate |
Detailed scenario logic:
Scenario A: Latest FDK NOT installed + Platform 2.x manifest
Conditions:
FDK_MAJOR!= 10 (either 9 or not found)MANIFEST_PLATFORMin ["2.3", "2.2", "2.1", missing, or < "3.0"]MANIFEST_FDKstarts with "9." orMANIFEST_NODEstarts with "18."
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 · 320 lines · 19 tokens per session scan C 321920266970
smart-prerequisites-check is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It adds 19 tokens to every session and 2,691 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other cursor rules, from other repositories
battle-tested-engineer
Battle-tested engineering judgment for code, refactors, tests, and frontend UI. Ultra-terse caveman style during code work.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.