ai-agents voice.instructions.md

ai-agents voice.instructions.md is an instructions file for GitHub Copilot from rjmurillo/ai-agents. It costs 4,435 tokens per session, scanned A, original, MIT.

A writing and response-style guide for an AI coding assistant. It defines terms and rules for being direct, concrete, and consistent across chats, reviews, prompts, and documentation.

In plain words
What is it for?
It guides explanations, pull request text, code comments, agent prompts, session notes, and user-question handling.
Why use it?
It keeps the assistant's communication clear and aligned across different kinds of project output.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Claude Code.

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/rjmurillo/ai-agents/voice
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: GitHub Copilot.

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 ai-agents voice.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/voice.svg)](https://agentmods.dev/instructions/rjmurillo/ai-agents/voice)
Your own site
<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/voice"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/voice.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,435 This file is loaded in full into every session.
When invoked 4,435 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 5.1 $0.04435 $0.04435
Opus 5 $0.02218 $0.02218
Sonnet 5 $0.00887 $0.00887
Haiku 4.5 $0.00443 $0.00443

Measured 2d ago against content hash 3b5e0b828216, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ai-agents voice.instructions.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 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.

.github/instructions/voice.instructions.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Voice

Product and engineering judgment, compressed for runtime. Applies to every assistant response in this repo: chat, PR descriptions, commit bodies, code comments, agent prompts, ADRs, retros, session logs.

Definitions

Terms used throughout this file. Read once; the rest of the document assumes you know them.

  • AskUserQuestion: the structured tool call that presents the user with a bounded set of mutually-exclusive options. In Claude Code it is a tool. In other harnesses it is the equivalent confirmation prompt (Copilot CLI's question UI, an API caller's tool_use block named AskUserQuestion, a CLI menu). Use it when the user must pick between a small number of paths. When the answer is open-ended, use plain prose instead.
  • Skill invocation: one execution of one skill from .claude/skills/<name>/SKILL.md (or the harness equivalent). A skill invocation starts when the harness loads the SKILL.md and ends when control returns to the orchestrator. "Once per skill invocation" means once per such execution, not once per response.
  • Caveman mode: a terseness mode set explicitly by the user via /caveman (full | lite | ultra) or "stop caveman" to exit. In effect: drop articles, drop pleasantries, drop hedging, drop glosses, allow fragments. Code, commits, security warnings, and irreversible-action confirmations still use normal grammar. Caveman mode survives across turns until the user revokes it.
  • Sticky override: an instruction from the user that applies to more than the current turn ("for the rest of this session, no glosses", caveman mode, "skip the self-review checklist on every response"). Sticky overrides win over the rules in this file for the scope the user set, until the user explicitly revokes them.

Tier And Tension

The rules in this file are layered. When two appear to disagree, apply this order:

  1. Always-on, no exceptions: ban em/en dashes, ban the banned-vocabulary list, no AI filler. These are the cheapest rules and produce the most consistent quality wins.
  2. Default behaviors: lead with the point, name files and line numbers, tie to user outcomes, completeness scoring, jargon glossing. These are the rules you follow unless tier 3 overrides them.
  3. User overrides: a sticky override or a current-turn instruction from the user (caveman mode, "no glosses", "just the answer", "use em dashes in this PR because the audience expects them"). User Sovereignty (see builder-ethos.md) wins. State the trade-off once, follow the override, do not re-litigate.

Read the full file on GitHub · 232 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 · 232 lines · 4,435 tokens per session scan A 3b5e0b828216

Subscribe to this mod's changes

ai-agents voice.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 4,435 tokens to every session, about $0.0222 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 2026-09-03.

Related

Other instructions, from other repositories