confusion

A decision guide for unclear app-development requests. It explains how to resolve common choices such as OAuth versus an API token, automatic versus manual triggers, and frontend versus serverless work.

In plain words
What is it for?
Use it to choose authentication, triggers, event handling and error-handling approaches for app integrations.
Why use it?
It reduces guesswork when a request leaves important implementation details unspecified.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/freshworks-developers/fw-dev-tools/confusion
Clone the repo
git clone --depth 1 https://github.com/freshworks-developers/fw-dev-tools
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01345
Opus 5 $0.00000 $0.00673
Sonnet 5 $0.00000 $0.00269
Haiku 4.5 $0.00000 $0.00135

Measured 2d ago against content hash e3233bf1d3a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

confusion 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.

skills/fw-app-dev/rules/confusion.mdc · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

App Development Disambiguation Guide

When to use: Prompt is vague, incomplete, or could be interpreted multiple ways.

Top 5 Common Ambiguities

1. OAuth vs API Token?

Ambiguous patterns:

  • "integrate with [service]"
  • "connect to [API]"
  • No mention of authentication

Decision:

Does service support OAuth?
├─ YES → Is it user-facing (users have accounts)?
│   ├─ YES → Use OAuth (GitHub, Jira, Salesforce, Google)
│   └─ NO → Use API Token (simpler for admin services)
└─ NO → Use API Token (Zapier webhooks, custom APIs)

Implementation:

  • OAuth: config/oauth_config.json with integrations wrapper
  • API Token: config/iparams.json with "secure": true

2. Automatic vs Manual Trigger?

Ambiguous patterns:

  • "logs data to [service]"
  • "sends information to [platform]"
  • "creates [item] from ticket"

Decision:

What's the purpose?
├─ LOGGING/ARCHIVING → Automatic (serverless events)
│   Examples: "logs tickets", "archives data"
│   Why: Must happen without user action
│
├─ NOTIFICATION/ALERT → Automatic (serverless events)
│   Examples: "sends alerts", "notifies team"
│   Why: Must be timely
│
├─ ACTION/CREATION → Manual (button in UI)
│   Examples: "creates issue", "generates card"
│   Why: User decides when to create
│
└─ UNCLEAR → Ask user or default to Manual (safer)

Implementation:

  • Automatic: Serverless with onTicketCreate, onTicketUpdate events
  • Manual: Hybrid with button in sidebar + SMI function

3. Frontend vs Serverless?

Ambiguous patterns:

  • "app that syncs data"
  • "app that sends webhooks"
  • No mention of UI

Decision:

Does user need to SEE or INTERACT with the app?
├─ YES → Frontend or Hybrid
│   Examples: View status, trigger actions, configure settings
│
└─ NO → Serverless only
    Examples: Pure automation, background sync, webhook forwarding

Default rule: When in doubt, include frontend (Hybrid). Users almost always want to see what's happening.

Read the full file on GitHub · 173 lines

Changes

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.

  1. 2d ago First seen · 173 lines · 0 tokens per session scan A e3233bf1d3a8

Subscribe to this mod's changes

confusion is a cursor rule published in the GitHub repository freshworks-developers/fw-dev-tools (5 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,345 tokens. 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.