A writing-voice tool that studies sample copy or interviews you, then records a reusable project voice guide. It keeps the project's core voice consistent while adjusting formality, energy, and technical depth for each channel.

Use it to extract a voice from examples, create `/ref/tone-guide.md`, adapt copy for emails, slides, chat summaries, or source documents, and validate and explain suggested edits.

It prevents different drafts or channels from sounding like they were written by unrelated people. It also makes the project's preferred terms and banned phrases available for future checks.

tune-voice — Skill for Claude Code by digital-stoic-org

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.

Any agent

npx skills add digital-stoic-org/agent-skills --skill tune-voice

Clone the repo

git clone --depth 1 https://github.com/digital-stoic-org/agent-skills

Made for: Claude Code.

Or install content, the plugin that ships this one along with the rest of its 7 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/tune-voice/github.svg)](https://agentmods.dev/skills/digital-stoic-org/agent-skills/tune-voice)

Your own site

<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/tune-voice"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/tune-voice/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/tune-voice"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/tune-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,222 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 12
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00116	$0.02222
Opus 5	$0.00058	$0.01111
Sonnet 5	$0.00023	$0.00444
Haiku 4.5	$0.00012	$0.00222

Measured 11d ago against content hash fe21b9702620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tune-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 11d 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.

content/skills/tune-voice/SKILL.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tune Voice — Per-Project Voice Extraction & Enforcement

Give a project a durable, reusable writing voice. The voice is a project artifact — it lives at <project>/ref/tone-guide.md, not in global memory — so each project keeps its own voice and drafts can be checked against it.

Fork-and-adapt lineage (design borrowed, storage owned): 9-dimension profile + anti-performative guardrails from entpnomad/tone-of-voice; voice-constant / tone-flex + validate-and-explain from brand-voice-enforcement; extract-from-samples from affaan-m/brand-voice.

Model: voice is constant, tone flexes

Voice constant — identity, beliefs, audience, traits, terminology, banned phrases. Never changes across a project's copy.
Tone flexes on three axes — formality · energy · technical depth — per channel (slide vs. Slack recap vs. cold email vs. golden-source doc).

A profile captures both. Enforcement holds the constant and picks the tone-flex for the channel at hand.

Step 0: Resolve the profile path

Read $PRAXIS_DIR/config/projects.yaml. Match --project <alias> against project keys (case-insensitive); if a name is given instead, fuzzy-match name fields. If no --project, infer from the working directory (which project's praxis: path is an ancestor of cwd), else ask.
Profile path = <project praxis root>/ref/tone-guide.md, where the praxis root is the praxis: value for that alias (resolve /praxis/..., /repos/... aliases via .claude/paths.md).
Leaf projects (a praxis: path with sub-projects, e.g. Slasheo's guide lives under ai-school-tech/ref/): accept an explicit --path <dir> override, or Glob for an existing **/ref/tone-guide.md under the project root and reuse it.
Guards: if $PRAXIS_DIR unset → ⚠️ $PRAXIS_DIR not set. export PRAXIS_DIR="$HOME/dev/praxis". If config missing → ⚠️ No project config at $PRAXIS_DIR/config/projects.yaml.

Modes

Mode	Command	Purpose
extract	`extract <files/globs>`	Reverse-engineer a profile FROM real copy → write `ref/tone-guide.md`
interview	`interview`	Build a profile from a 9-question interview (fallback when no samples exist)
apply	`apply <file>`	Rewrite/check a draft against the profile; validate and explain edits
show	`show`	Print the current profile (or a named section)

Read the full file on GitHub · 173 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.

11d ago First seen · 173 lines · 116 tokens per session scan A fe21b9702620

Subscribe to this mod's changes

tune-voice is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 116 tokens to every session and 2,222 once invoked, about $0.0006 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.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens