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.
npx agentmods add instructions/rjmurillo/ai-agents/voicegit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/instructions/rjmurillo/ai-agents/voice)<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>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 | $0.04435 | $0.04435 |
| Opus 5 | $0.02218 | $0.02218 |
| Sonnet 5 | $0.00887 | $0.00887 |
| Haiku 4.5 | $0.00443 | $0.00443 |
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.
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'stool_useblock namedAskUserQuestion, 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:
- 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.
- 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.
- 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.
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.
- 2d ago First seen · 232 lines · 4,435 tokens per session scan A 3b5e0b828216
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.
Other instructions, from other repositories
abtars AGENTS.md
AGENTS.md instructions for aksika/abtars, covering agents.md, quick commands, architecture, model-call chokepoint: spin(spec) (#1271) and external dependency: abmind.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.
gameforge AGENTS.md
Instructions for robcost/gameforge, covering general guidelines for working with nx, scaffolding & generators and when to use nxdocs.
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).
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.
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.