speech-swift AGENTS.md

speech-swift AGENTS.md is an instructions file for Codex, OpenCode from soniqo/speech-swift. It costs 5,053 tokens per session, scanned A, original, Apache-2.0.

Development instructions for speech-swift, a set of Apple Silicon speech models that handle tasks such as speech recognition, speech generation, speaker identification, and voice processing. They cover communication style, workflow, testing, benchmarks, memory use, and Git practices.

In plain words
What is it for?
Use them when changing speech models, Swift code, benchmarks, tests, pull requests, or development documentation for Apple Silicon.
Why use it?
They make technical updates easier to review and reduce failures caused by unsafe parallel work, overlooked tests, or excessive memory use. They also require separate work areas when multiple agents are active.

Instructions file for CodexOpenCode

About the project

Speech Swift is a collection of Apple Silicon speech tools for recognizing, generating, transforming, and analyzing audio locally with MLX Swift and CoreML. It is for Mac and iOS applications that need on-device speech features such as transcription, voice agents, synthesis, and speaker identification; the catalogue entries provide instructions and skills for using it.

soniqo/speech-swift · 1,165 stars · on GitHub

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 instructions/soniqo/speech-swift/agents-md
Clone the repo
git clone --depth 1 https://github.com/soniqo/speech-swift

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 speech-swift AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/soniqo/speech-swift/agents-md.svg)](https://agentmods.dev/instructions/soniqo/speech-swift/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/soniqo/speech-swift/agents-md"><img src="https://agentmods.dev/badge/instructions/soniqo/speech-swift/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,053 This file is loaded in full into every session.
When invoked 5,053 The same file — it is already loaded in full.
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 $0.05053 $0.05053
Opus 5 $0.02527 $0.02527
Sonnet 5 $0.01011 $0.01011
Haiku 4.5 $0.00505 $0.00505

Measured today against content hash 98fa682ddd2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speech-swift 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 today.

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 · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

AI speech models for Apple Silicon (MLX Swift). ASR, TTS, speech-to-speech, VAD, diarization, speech enhancement.

Communication Style

  • Communicate at the conceptual level first: what changed, why it matters, risk, tests, and recommendation.
  • Keep status updates short and understandable. Do not dump command logs, low-level mechanics, or long implementation detail unless directly asked.
  • For PRs and fixes, default to this summary shape: what changed, architecture fit, regression risk, tests run or needed, and recommendation.
  • If there are bugs, blockers, or regression risks, lead with them clearly and briefly.
  • When the user asks a direct question, answer it directly before adding supporting detail.

Workflow

  • Always work in a separate git worktree so concurrent agents don't fight over the same working directory. Create one with git worktree add ../speech-swift-<task> <branch>, do all edits there, push from there. Multiple agents may be running against this repo at the same time — checking out branches in the shared working copy clobbers their state and silently loses WIP files. Delete the worktree (git worktree remove) when the task is done.
  • Never commit, push, or comment on GitHub without explicit user confirmation. Draft first, ask to confirm, then execute.
  • Every README.md change must update all 13 translations (README_zh.md, README_ja.md, README_ko.md, README_es.md, README_de.md, README_fr.md, README_hi.md, README_pt.md, README_ru.md, README_ar.md, README_th.md, README_tr.md, README_vi.md). No exceptions.
  • Keep docs and comments scoped to this package. Model docs, code comments, and PR descriptions describe this package's models, APIs, and formats only — never downstream consumer apps or their integration rules.

Running Tests and Benchmarks — Sequential and Memory-Aware

Heavy operations in this repo load multi-gigabyte CoreML/MLX models. Run them strictly one at a time — overlapping them has exhausted memory and rebooted development machines.

Read the full file on GitHub · 359 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. today Changed · +2 lines · +52 tokens per session 98fa682ddd2b
  2. 5d ago First seen · 357 lines · 5,001 tokens per session scan A cf8fe40d6906

Subscribe to this mod's changes

speech-swift AGENTS.md is an instructions file published in the GitHub repository soniqo/speech-swift (1,165 stars, last pushed today), licensed Apache-2.0. It adds 5,053 tokens to every session, about $0.0253 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 2026-08-30.

Related

Other instructions, from other repositories

FluidAudio CLAUDE.md

Claude Code instructions for FluidInference/FluidAudio, covering claude.md, project overview, critical development rules, never use @unchecked sendable and never create dummy models or synthetic data.

FluidInference/FluidAudio · 2,543 tokens

FluidAudio copilot-instructions.md

Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).

FluidInference/FluidAudio · 552 tokens

Vocello AGENTS.md

AGENTS.md instructions for PowerBeef/Vocello, covering agents.md — vocello (qwenvoice), product and authority, start and resume work, hard invariants and domain routing.

PowerBeef/Vocello · 5,217 tokens

Logue CLAUDE.md

Instructions for bitwize-ai/Logue, covering logue — development guidelines, project overview, running the build you just made, where documentation goes and dependencies.

bitwize-ai/Logue · 7,535 tokens

localvoxtral AGENTS.md

AGENTS.md instructions for T0mSIlver/localvoxtral, covering localvoxtral — agent guide, build & test — read this first on a non-mac dev box, proof culture — non-negotiable, test tiers — the short version and ci / shipping.

T0mSIlver/localvoxtral · 2,917 tokens

OpenSuperMLX AGENTS.md

AGENTS.md instructions for axot/OpenSuperMLX, covering agents.md — opensupermlx, agent behavioral guidelines, 1. think before coding, 2. simplicity first and 3. surgical changes.

axot/OpenSuperMLX · 5,990 tokens