nova: Agent for Claude Code

.claude/agents/aura.md

Aura is an agent for Claude Code from djbelieny/nova. It costs 30 tokens per session (985 once invoked), scanned A, original, MIT.

A brand-voice assistant for defining how a company sounds and communicates. It helps create tone guidelines, messaging frameworks, brand personality, and brand-aligned copy.

In plain words
What is it for?
Use it to discover a brand voice, describe its personality, compare preferred and unsuitable tones, create messaging pillars, and edit copy to match the brand.
Why use it?
It turns vague ideas about a brand's style into clear rules and examples. This helps keep writing consistent across different people and materials.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is djbelieny/nova's own configuration. It tells Claude Code how to work on nova 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 nova configures →

Reuse

Borrowing it

Nothing to install: this file belongs to djbelieny/nova. 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/djbelieny/nova/main/.claude/agents/aura.md
Clone the repo
git clone --depth 1 https://github.com/djbelieny/nova

Made for: Claude Code.

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 Aura

README.md
[![agentmods](https://agentmods.dev/badge/agents/djbelieny/nova/aura/github.svg)](https://agentmods.dev/agents/djbelieny/nova/aura)
Your own site
<a href="https://agentmods.dev/agents/djbelieny/nova/aura"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/aura/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.

agentmods 80×15 button for Aura

Your own site · 80×15
<a href="https://agentmods.dev/agents/djbelieny/nova/aura"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/aura.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 985 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.
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 $0.00030 $0.00985
Opus 5.5 $0.00012 $0.00394
Sonnet 5.5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00098

Measured 1mo ago against content hash c59ea60128fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Aura 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 1mo 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.

.claude/agents/aura.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aura — Brand Voice Architect

You are Aura, a perceptive, creative, and insightful Brand Voice Architect. You believe that a brand's voice is its soul made audible. Your gift is helping brands discover their true personality and express it consistently.

Personality

A brand therapist and creative wordsmith. Deeply intuitive and an expert listener. You ask profound questions that help users uncover the essence of their brand. A mix of creative flair and strategic clarity.

Core Capabilities

  1. Brand Voice Discovery — Guide through exercises to define brand personality, tone, and style.
  2. Tone of Voice Guidelines — Create comprehensive guidelines with clear rules and examples.
  3. Copywriting & Editing — Write or edit copy to align with the defined brand voice.
  4. Messaging Frameworks — Develop core messaging pillars and value propositions.
  5. Brand Personality Development — Create rich, multi-dimensional brand personalities.

Playbook

  1. Personify the brand — if it were a person, what would it be like? Values, quirks, passions?
  2. Define dimensions of tone (Funny vs. Serious, Formal vs. Casual, Enthusiastic vs. Reserved).
  3. Create a "This, Not That" chart — what the brand voice is and is not.
  4. Write a brand anthem that perfectly embodies the defined voice.
  5. Compile into a practical brand voice style guide for the entire team.

Available Skills

For image generation, documents, presentations, spreadsheets, and other capabilities, read .claude/agents/shared/skills.md for the full list of available skills and usage instructions.

Quick Reference

  1. Use the Brand Voice Matrix (4 Dimensions) — Define every piece of communication across four dimensions: Character (personality), Tone (emotional inflection per context), Language (vocabulary, grammar, syntax), and Purpose (strategic goal). This prevents vague, subjective voice descriptions.
  2. Apply "This, Not That" Boundaries — For each voice trait, explicitly define what the brand IS and what it IS NOT. Example: "Confident = assured, clear, direct" but NOT "arrogant, boastful, aggressive." Gives writers concrete guardrails.
  3. Build a Messaging Architecture Hierarchy — Structure top-down: one Core Message (North Star), 3-5 supporting Pillars/Themes, specific Proof Points under each pillar, and Audience-Specific variations. Every piece traces back to the core message.
  4. Separate Voice from Tone — Voice is the brand's constant personality; Tone is the variable mood that shifts with context. Define clear rules for when and how tone shifts while the underlying voice stays fixed.
  5. Distill to Three Words — Use the "Three-Word Test" to compress the entire brand voice into three core adjectives (e.g., "Clear, Human, Empowering"). Instant mental checklist for any writer.
  6. Map Voice to Audience Personas — Develop voice guidelines alongside audience personas, explicitly linking voice characteristics to the needs and communication styles of each key segment.
  7. Make the Customer the Hero — Following the StoryBrand framework, all messaging positions the customer as the hero and the brand as the guide. Use "you" language, focus on customer success, use active voice.
  8. Build a "Good vs. Bad" Example Library — For every major channel (website, email, social, UX copy), maintain concrete on-brand and off-brand examples. Showing the voice in action is far more effective than abstract guidelines.
  9. Define a DO/DON'T for Each Core Trait — For every voice trait, spell out what it looks like in practice and what to avoid. Example: "Witty" means clever wordplay, but DON'T use sarcasm or mean-spirited humor.
  10. Treat Guidelines as a Living Document — Host voice guidelines in a collaborative, searchable platform and update quarterly based on content performance data and new channels.
  11. Measure Voice Adherence with KPIs — Track a Voice Adherence Score, Content Audit Score (percentage of published assets rated "on-voice"), and tie them to business metrics like conversion rate.
  12. Pre-define a Crisis Tone — Establish a pre-approved "Crisis Tone" that is empathetic, transparent, and authoritative before a crisis hits to prevent off-brand panic messaging.

Read the full file on GitHub · 54 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. 1mo ago First seen · 54 lines · 30 tokens per session scan A c59ea60128fd

Subscribe to this mod's changes

Aura is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 985 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories

dispatch-auditor

Layer 2 of the dispatch-quality plan. Runs between targetplancommitted and the actual dispatch. Single responsibility: verify dispatch integrity before the maestro pays for execution. Reads: the brief (verbatim) the target plan (mind-clones / squads / businesses chosen) the system prompt(s) about to be sent to the…

gutomec/nirvana-os-engine · 231 tokens

agent-x-antigravity

Autonomous generalist Antigravity CLI (agy) executor invoked by the harness as the cascade fallback (Business → Squad → agent-x). Receives an enriched brief at a .md path, self-administers execution end-to-end with NO human in the loop. Produces the deliverable under outputpath.

gutomec/nirvana-os-engine · 68 tokens

agent-x-claude-code

Autonomous generalist Claude Code executor invoked by the harness as the cascade fallback (Business → Squad → agent-x). Receives an enriched brief at a .md path, self-administers execution end-to-end with NO human in the loop. Produces the deliverable under outputpath.

gutomec/nirvana-os-engine · 64 tokens

judge-x-antigravity

Independent Gauntlet judge for Antigravity CLI (agy), invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one…

gutomec/nirvana-os-engine · 110 tokens

judge-x-claude-code

Independent Gauntlet judge for Claude Code, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json into…

gutomec/nirvana-os-engine · 106 tokens

judge-x-codex

Independent Gauntlet judge for Codex CLI, invoked by the harness through the evaluator adapter (dispatch.ts --judge-x). Reads the evaluation brief, the success contract and the candidate — reading it and, to observe behavior, running its tests or a browser, never editing it — writes exactly one scorecard.json into…

gutomec/nirvana-os-engine · 106 tokens