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/freshworks-platform3git 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/rules/freshworks-developers/fw-dev-tools/freshworks-platform3)<a href="https://agentmods.dev/rules/freshworks-developers/fw-dev-tools/freshworks-platform3"><img src="https://agentmods.dev/badge/rules/freshworks-developers/fw-dev-tools/freshworks-platform3.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 | $0.01990 | $0.01990 |
| Opus 5 | $0.00995 | $0.00995 |
| Sonnet 5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
freshworks-platform3 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Freshworks Platform 3.0 Enforcement
Role: Strict enforcement layer with ZERO TOLERANCE for Platform 2.x patterns.
Immediate Rejection Patterns
[INVALID] NEVER Generate These (Platform 2.x)
| Pattern | Platform 2.x (FORBIDDEN) | Platform 3.0 (REQUIRED) |
|---|---|---|
| Manifest structure | "product": { "freshdesk": {} } |
"modules": { "common": {}, "support_ticket": {} } |
| Platform version | "platform-version": "2.3" |
"platform-version": "3.0" |
| Domain whitelist | "whitelisted-domains": ["https://..."] |
Request templates in config/requests.json |
| Request API | $request.post('url', opts) |
$request.invokeTemplate('templateName', {}) |
| UI components (vanilla JS) | <button>, <input>, <select> |
<fw-button>, <fw-input>, <fw-select> (Crayons CDN) |
| UI components (React Meta) | Crayons, <fw-*> |
DEW React components from @freshworks/dew-components |
| OAuth structure | Flat config | { "integrations": { "service": {...} } } |
[VALID] ALWAYS Enforce These (Platform 3.0)
- Engines: New apps MUST start with
"engines": { "node": "24.11.0", "fdk": "10.0.1" }. fw-app-dev does not install fdk or Node — use fw-setup (or prompt the user to add it; SKILL.md → FDK / Node.js toolchain — not provided by fw-app-dev). Prefer fw-setup if validate will not run. One-time downgrade to"node": "18.20.8", "fdk": "9.8.2"is LAST RESORT only after sixfdk validatefix iterations (or CLI cannot run on 10.0.1+24.11.0) and toolchain-only failure — full rules in SKILL.md. - Manifest:
"platform-version": "3.0"with"modules"structure - Request Templates: FQDN hosts only (no paths), use
<%= variable %>syntax - UI components: Vanilla JS apps → Crayons (
fw-*). React Meta apps →@freshworks/dew-components+@freshworks/dew-stylesonly; never Crayons in Meta workflow. See react-meta-patterns.mdc andreferences/react-meta/dew-components.md. - Request API: Only
$request.invokeTemplate()(never.post(),.get(), etc.) - OAuth: Must have
integrationswrapper inoauth_config.json
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 · 217 lines · 1,990 tokens per session scan A 94f169ff856b
freshworks-platform3 is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 9d ago), licensed MIT. It adds 1,990 tokens to every session, about $0.0100 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 cursor rules, from other repositories
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.
family-instance-domain-actions
Family instance domain action implementation patterns.