push-2-talk: Instructions file for Codex

AGENTS.md

push-2-talk AGENTS.md is an instructions file for Codex, OpenCode from yyyzl/push-2-talk. It costs 1,737 tokens per session, scanned A, original, MIT.

A repository instruction file for Push-to-Talk, a desktop application with a React and TypeScript interface and a Rust backend. It maps the main frontend, backend, test, and build directories.

In plain words
What is it for?
Navigating the project, locating speech recognition and text-processing code, and finding build and regression-test commands.
Why use it?
It helps an agent find the correct part of the application instead of mixing user-interface, speech-processing, and native backend changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md.

This is yyyzl/push-2-talk's own configuration. It tells Codex and OpenCode how to work on push-2-talk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything push-2-talk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yyyzl/push-2-talk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yyyzl/push-2-talk/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/yyyzl/push-2-talk

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for push-2-talk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yyyzl/push-2-talk/agents-md/github.svg)](https://agentmods.dev/instructions/yyyzl/push-2-talk/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yyyzl/push-2-talk/agents-md"><img src="https://agentmods.dev/badge/instructions/yyyzl/push-2-talk/agents-md/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.

agentmods 80×15 button for push-2-talk AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/yyyzl/push-2-talk/agents-md"><img src="https://agentmods.dev/badge/instructions/yyyzl/push-2-talk/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,737 This file is loaded in full into every session.
When invoked 1,737 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01737 $0.01737
Opus 5.5 $0.00695 $0.00695
Sonnet 5.5 $0.00347 $0.00347
Haiku 4.5 $0.00174 $0.00174

Measured 1mo ago against content hash 3b9268bf7d81, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

push-2-talk AGENTS.md 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.

AGENTS.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

  • src/ holds the React + TypeScript UI (main window, overlay, and notification windows).
  • index.html, overlay.html, and notification.html are the Vite entry points for the three windows.
  • src-tauri/ contains the Rust backend, src-tauri/tauri.conf.json, and app icons in src-tauri/icons/.
  • ui/ is for auxiliary UI assets or prototypes used by the frontend.
  • scripts/ has build/release helpers; dist/ is generated frontend output.
  • tests/ contains TypeScript runtime regression tests (tsx --test).

Key Backend Modules (src-tauri/src/)

  • asr/ - Multi-provider ASR with HTTP and realtime modes (Qwen, Doubao, Doubao IME, SenseVoice)
  • pipeline/ - Processing pipelines for dictation and assistant modes
  • tnl/ - Technical Normalization Layer between ASR and LLM (pinyin/phonetic matching, letter merge, hyphen rewrite)
  • learning/ - Auto vocabulary learning (coordinator, diff_analyzer, llm_judge, validator, store)
  • builtin_dictionary_updater.rs - Remote builtin hotwords fetch + atomic cache persistence + runtime refresh events
  • platform/ - Native capability factory, Windows and macOS implementations
  • platform/windows/uia_text_reader.rs - Windows UI Automation text capture
  • openai_client.rs - Shared LLM client with connection testing
  • config.rs - Configuration management with automatic migration

Key Frontend Structure (src/)

  • pages/ - Page components (Dashboard, ASR, Models, LLM, Assistant, Hotkeys, Dictionary, Preferences, History, Help)
  • components/ - Reusable UI components (common/, layout/, learning/, live/, modals/, history/, notice/)
  • windows/ - Overlay and notification window components
  • hooks/ - Custom React hooks (useAppServiceController, useDictionary, useHotkeyRecording, useUpdater, useTauriEventListeners)
  • types/ - TypeScript type definitions
  • utils/ - Utility functions (dictionaryUtils)

Build, Test, and Development Commands

  • npm install installs frontend dependencies.
  • npm run dev starts the Vite dev server for the UI.
  • npm run build type-checks and builds the frontend bundle.
  • npm run preview serves the built UI locally.
  • npm run test:ts runs TypeScript runtime tests in tests/*.test.ts.
  • npm run tauri dev runs the desktop app in dev mode; follow the administrator workflow on Windows and grant native privacy permissions on macOS.
  • npm run tauri build builds the native platform bundles; Windows uses NSIS and macOS uses tauri.macos.conf.json. Output is in src-tauri/target/release/bundle/. See PLATFORM_ARCHITECTURE.md for Mac dependencies and prototype packaging.
  • cd src-tauri then cargo build, cargo check, or cargo test for the Rust backend.
  • cd src-tauri then cargo run --features cli-tools --bin test_api to manually verify ASR API behavior.

Read the full file on GitHub · 92 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. 1mo ago Changed · -61 lines · -711 tokens per session 3b9268bf7d81
  2. 2mo ago First seen · 153 lines · 2,448 tokens per session scan A d822486c7360

Subscribe to this mod's changes

push-2-talk AGENTS.md is an instructions file published in the GitHub repository yyyzl/push-2-talk (185 stars, last pushed 1mo ago), licensed MIT. It adds 1,737 tokens to every session, about $0.0069 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 2026-08-30.

Related

push-2-talk AGENTS.md compared with instructions from other repositories

push-2-talk AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
push-2-talk AGENTS.mdyyyzl/push-2-talkInstructions file1851mo agoMITA1,737Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode