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/zeyadelosherey/tapwisper-desktopWrote 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/zeyadelosherey/tapwisper-desktop/project-overview)<a href="https://agentmods.dev/rules/zeyadelosherey/tapwisper-desktop/project-overview"><img src="https://agentmods.dev/badge/rules/zeyadelosherey/tapwisper-desktop/project-overview.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 5.1 | $0.00716 | $0.00716 |
| Opus 5 | $0.00358 | $0.00358 |
| Sonnet 5 | $0.00143 | $0.00143 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
project-overview 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 8d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TapWisper Desktop
Open-source, system-wide voice dictation with AI, built with Electron 33 + React 19 + TypeScript + Tailwind CSS.
Architecture
Three Electron processes:
- Main (
src/main/) -- system tray, global shortcuts, window management, IPC handlers, clipboard, audio recording, permission checking, SQLite database, config store - Preload (
src/preload/) -- context bridge exposingwindow.tapwisper.*API to the renderer - Renderer (
src/renderer/) -- React UI with Tailwind CSS, Zustand state, Framer Motion animations
Multi-Window System
| Window | Purpose |
|---|---|
| Main Window | Settings and configuration (1000x700) |
| Recording Pill | Floating recording indicator (140x50) |
| Pinned Panel | Persistent recording panel |
| Command Popup | Action/command selector overlay |
| AI Panel | AI suggestion overlay |
Overlay windows use hash-based routing (#/recording-pill, #/pinned-panel, etc.) and are pre-warmed to avoid first-use delay.
Directory Map
src/
main/ # Electron main process
preload/ # Context bridge (secure IPC)
renderer/
components/ # Overlay UI components
pages/ # Settings window pages (includes onboarding)
services/ # AI provider clients (Gemini, OpenAI, Claude, Together, Soniox)
hooks/ # React hooks (audio, shortcuts, AI actions)
store/ # Zustand state stores (stats, activity)
models/ # TypeScript type definitions
constants/ # Shared constants (colors, providers)
utils/ # Utility functions (formatting)
i18n/ # Translations (en, ar, de, es, fr, it)
assets/ # Static assets (logos)
styles/ # Global CSS and theme variables
types/ # Global type declarations
Key Patterns
- IPC: All renderer-to-main communication goes through
window.tapwisper.*(defined in preload) - Permissions:
src/main/permissions.tschecks/requests platform-specific permissions; exposed viawindow.tapwisper.permissions.* - Onboarding: First-launch permission setup in
src/renderer/pages/onboarding.tsx, gated inmain-window.tsx - AI Router:
src/renderer/services/ai-router.tsroutes requests to the configured LLM/voice provider - AI Providers: Gemini, Together AI, OpenAI, Claude (LLM); Together Whisper, Soniox (voice)
- Path Alias:
@/maps tosrc/renderer/(configured in electron-vite)
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.
- 8d ago First seen · 72 lines · 716 tokens per session scan A 233d3c98ae91
project-overview is a cursor rule published in the GitHub repository zeyadelosherey/tapwisper-desktop (5 stars, last pushed 4mo ago), licensed MIT. It adds 716 tokens to every session, about $0.0036 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
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.
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.