enforce-voice

enforce-voice is a command for coding agents from anthropics/knowledge-work-plugins. It costs 6 tokens per session (421 once invoked), scanned A, original, Apache-2.0.

A command that loads a company’s brand guidelines and uses them when creating content.

In plain words
What is it for?
Applying saved or session-specific brand rules to emails, proposals, presentations, and other content.
Why use it?
It reduces the risk of producing content with the wrong tone, terminology, or messaging.

Command

Part of the brand-voice plugin — 3 skills, 3 commands, 5 agents shipped together

About the project

Knowledge Work Plugins is an open-source collection of Claude extensions organized around roles such as productivity, sales, and customer support. Each plugin combines role-specific guidance, connectors, commands, and sub-agents so knowledge workers can use Claude with their team’s tools and processes. The catalogue entries are examples of, or workflows from, this plugin collection.

anthropics/knowledge-work-plugins · 23,877 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 commands/anthropics/knowledge-work-plugins/enforce-voice
Clone the repo
git clone --depth 1 https://github.com/anthropics/knowledge-work-plugins

Or install brand-voice, the plugin that ships this one along with the rest of its 3 skills, 3 commands, 5 agents.

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 enforce-voice

README.md
[![agentmods](https://agentmods.dev/badge/commands/anthropics/knowledge-work-plugins/enforce-voice.svg)](https://agentmods.dev/commands/anthropics/knowledge-work-plugins/enforce-voice)
Your own site
<a href="https://agentmods.dev/commands/anthropics/knowledge-work-plugins/enforce-voice"><img src="https://agentmods.dev/badge/commands/anthropics/knowledge-work-plugins/enforce-voice.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00006 $0.00421
Opus 5 $0.00003 $0.00211
Sonnet 5 $0.00001 $0.00084
Haiku 4.5 $0.00001 $0.00042

Measured yesterday against content hash ab67acc3ab40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

enforce-voice 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

partner-built/brand-voice/commands/enforce-voice.md · 23 lines

What it actually says

MANDATORY FIRST STEP — do this before anything else, including loading guidelines or processing the content request. Check whether the user has a working folder selected for this session. You must verify this before starting any enforcement work. If there is no working folder, stop and warn the user: "You don't have a working folder selected. Without one, I can't load saved guidelines from a previous session, and any guidelines generated in this conversation won't be saved for future sessions either. Please select a working folder and re-run this command. If you'd like to proceed anyway (guidelines will only be usable in this session), let me know." Wait for the user to confirm before continuing.

Load the user's brand guidelines and apply them to the content request provided in $ARGUMENTS.

Find brand guidelines using this sequence (stop as soon as found):

  1. Session context — check if guidelines were generated earlier in this conversation
  2. Local guidelines file — check for .claude/brand-voice-guidelines.md inside the user's working folder. Do NOT use a relative path from the agent's current working directory (in Cowork, the agent runs from a plugin cache directory). If no working folder is set, skip this step.
  3. If not found, ask the user to run /brand-voice:discover-brand, /brand-voice:generate-guidelines, or paste guidelines directly

Once guidelines are loaded, follow the brand-voice-enforcement skill instructions to:

  1. Analyze the content request (type, audience, key messages, requirements)
  2. Apply voice constants ("We Are / We Are Not") and flex tone for context (formality, energy, technical depth)
  3. Generate content applying voice, tone, messaging, and terminology guidelines
  4. Validate output against brand do's and don'ts
  5. Present the content with a brief explanation of brand choices made
  6. Note any open questions from guidelines that affect this content
  7. Offer to refine based on feedback
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. yesterday First seen · 23 lines · 6 tokens per session scan A ab67acc3ab40

Subscribe to this mod's changes

enforce-voice is a command published in the GitHub repository anthropics/knowledge-work-plugins (23,877 stars, last pushed today), licensed Apache-2.0. It adds 6 tokens to every session and 421 once invoked, about $0.0000 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.