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.
git 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/validation-workflow)<a href="https://agentmods.dev/rules/freshworks-developers/fw-dev-tools/validation-workflow"><img src="https://agentmods.dev/badge/rules/freshworks-developers/fw-dev-tools/validation-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/freshworks-developers/fw-dev-tools/validation-workflow"><img src="https://agentmods.dev/badge/rules/freshworks-developers/fw-dev-tools/validation-workflow.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02338 | $0.02338 |
| Opus 5.5 | $0.00935 | $0.00935 |
| Sonnet 5.5 | $0.00468 | $0.00468 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
validation-workflow 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 1mo 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation & Auto-Fix Workflow
🚨 ZERO TOLERANCE: App is NEVER complete until ALL errors (platform AND lint) are fixed.
FDK / Node are not installed by fw-app-dev. This rule file and fw-app-dev edit app code and run fdk validate when the CLI exists; they do not install fdk, switch Node majors, or fix PATH / nvm. For that, use the fw-setup skill when present (/fw-setup-install, /fw-setup-upgrade, /fw-setup-use, /fw-setup-status). If fw-setup is missing, tell the user to add it (npx @freshworks/fw-dev-tools install). Canonical text: SKILL.md → FDK / Node.js toolchain — not provided by fw-app-dev.
REQUIRED FOR NEW APPS: FDK 10.0.1 + Node.js 24.x ("engines": { "node": "24.11.0", "fdk": "10.0.1" }). If fdk validate cannot start, use fw-setup first. LAST RESORT engines downgrade to FDK 9.8.2 + Node 18.20.8 is only after six validate+fix iterations or CLI cannot run on 10.0.1+24.11.0 under the conditions in SKILL.md (top section).
Before the first fdk validate: run the Manifest + toolchain gate in SKILL.md (node/fdk vs manifest.json → fw-setup / /fdk-migrate / align engines up). Never downgrade the shell or manifest to FDK 9 / Node 18 to silence engines mismatch when FDK 10 + Node 24 is installed.
Mandatory Workflow
Step 0: Gate (before any fdk validate)
Read manifest.json and compare to node --version / fdk version. Follow SKILL.md → Manifest + toolchain gate before any fdk validate. Do not skip for /fdk-fix, /fdk-refactor, or generation workflows. (For structured pre-submission review, use fw-review skill.)
Step 1: Automatic Validation After File Creation
AFTER creating ALL app files, AUTOMATICALLY run:
cd <app-directory>
fdk validate
DO NOT ask user to run it manually.
If the command fails before normal app validation, follow SKILL.md: fw-setup first; /fdk-migrate when platform-version is not 3.0; LAST RESORT downgrade only when that section’s bullets are satisfied (never as a substitute for migrate/setup).
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.
- 1mo ago First seen · 280 lines · 2,338 tokens per session scan A f53bc2738dbc
validation-workflow is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 29d ago), licensed MIT. It adds 2,338 tokens to every session, about $0.0094 per session on Opus 5.5. 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
pi-en
PI Cognitive AI. Trigger: $pi/coding/dev/code/architecture/API/refactor/debug/bug/error/exception/crash/timeout/performance/optimization/test/compile/git/release/verify/review/CR/product/requirements/ops/growth/design/team/support, or deep/2+ failures/looping/stuck/giving-up/retry/nevermind.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
prefer-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.