voicelayer: Instructions file for Codex

AGENTS.md

voicelayer AGENTS.md is an instructions file for Codex, OpenCode from EtanHey/voicelayer. It costs 2,682 tokens per session, scanned A, original, Apache-2.0.

Project instructions for working with VoiceLayer, a local voice interface for talking to coding agents. They describe the project’s priorities, boundaries, decisions, and known problems.

In plain words
What is it for?
Understanding VoiceLayer’s voice input, question-and-answer workflow, teleprompter, local-first design, and current user-experience gaps.
Why use it?
They give an agent the project context needed to make consistent decisions without rediscovering the owner’s preferences and constraints.

Instructions file for CodexOpenCode

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

This is EtanHey/voicelayer's own configuration. It tells Codex and OpenCode how to work on voicelayer 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 voicelayer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to EtanHey/voicelayer. 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/EtanHey/voicelayer/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/EtanHey/voicelayer

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 voicelayer AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/etanhey/voicelayer/agents-md.svg)](https://agentmods.dev/instructions/etanhey/voicelayer/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/etanhey/voicelayer/agents-md"><img src="https://agentmods.dev/badge/instructions/etanhey/voicelayer/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,682 This file is loaded in full into every session.
When invoked 2,682 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 $0.02682 $0.02682
Opus 5 $0.01341 $0.01341
Sonnet 5 $0.00536 $0.00536
Haiku 4.5 $0.00268 $0.00268

Measured today against content hash 7f09f70f0c5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

voicelayer 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 · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VoiceLayer

VoiceLayer is how I talk to my agents and how they talk back. I've been dictating through VoiceBar and F5 for a long time and that part does its job well. Asking is newer — I've been leaning on voice_ask heavily since late July 2026, gaining more and more experience with it, and it's become the thing that stops me losing answers and stops me getting walls of text I skim without actually understanding. I keep all this — rather than just paying for Wispr Flow — for three reasons: I can control it exactly how I want, the notch app we built beats anything that blocks my screen, and it's local-first. It hasn't replaced Wispr Flow, because Wispr Flow runs on my iPhone and this unfortunately doesn't, so this is what I use at my desk or pacing around the room. And there's still real work here: the teleprompter and the speech aren't synced at all — I can't click a word to jump back or scrub to a moment, so I end up waiting out the audio and reading the text from the MCP instead. I'm looking for things like that that would complete the UX, so other people installing this app can use it — or help, if they ever try to.

What I care about most

That what comes out is what I actually said. Today it drifts three ways — words get added that I never said, a sentence sometimes repeats back-to-back in a long transcript, and words I did say just vanish. All of it needs fixing — it isn't either/or. We fixed one of these by trimming and it cut real tails off my sentences. Don't fix it that way again — a fix that loses my words is worse than the bug.

Don't cut me off mid-thought. If I'm still talking there's no reason to time out — wait for me to think. Time out on silence, not on me. And every recording is kept — cancelled, timed out, all of them.

I want to be able to interrupt you mid-question and have you hear me. Barge-in was built and merged in May and then never wired into the live ask path — before anyone connects it, test whether that code is actually good enough to keep.

Read the full file on GitHub · 180 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 · +16 lines · +304 tokens per session 7f09f70f0c5c
  2. 6d ago First seen · 164 lines · 2,378 tokens per session scan A 8949c269907d

Subscribe to this mod's changes

voicelayer AGENTS.md is an instructions file published in the GitHub repository EtanHey/voicelayer (0 stars, last pushed today), licensed Apache-2.0. It adds 2,682 tokens to every session, about $0.0134 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens