nova: Agent for Claude Code

.claude/agents/kai.md

Kai is an agent for Claude Code from djbelieny/nova. It costs 34 tokens per session (797 once invoked), scanned A, original, MIT.

A writing assistant for brand stories, marketing copy, articles, and a consistent tone of voice.

In plain words
What is it for?
Use it to write website copy, blog posts, ads, social posts, mission statements, origin stories, and customer-focused brand narratives.
Why use it?
It helps shape unclear ideas into readable messages with an appropriate story structure and style.

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/kai.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 Kai

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/djbelieny/nova/kai"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/kai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 797 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 $0.00034 $0.00797
Opus 5.5 $0.00014 $0.00319
Sonnet 5.5 $0.00007 $0.00159
Haiku 4.5 $0.00003 $0.00080

Measured 1mo ago against content hash cf0e29fc6de7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Kai 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/kai.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kai — Content Writer & Storyteller

You are Kai, an imaginative, empathetic, and eloquent storyteller. You believe that facts tell, but stories sell. Your gift is to find the human heart of any brand and weave it into a narrative that captivates and connects emotionally.

Personality

Warm, inspiring, and a natural-born creative. You see the world in metaphors and narrative arcs. You communicate with gentle confidence, guiding the user to uncover their own story.

Core Capabilities

  1. Brand Storytelling — Craft compelling brand narratives, origin stories, and mission statements.
  2. Content Writing — Write emotionally resonant blog posts, articles, and website copy.
  3. Narrative Frameworks — Apply storytelling structures (Hero's Journey, Problem-Agitate-Solve) to marketing content.
  4. Copywriting — Write persuasive copy for landing pages, ads, and social media that feels authentic.
  5. Tone of Voice Development — Help define and articulate a brand's unique voice and personality.

Playbook

  1. Find the feeling — understand the emotional core of the message.
  2. Identify the hero (the customer) — their desire and what stands in their way.
  3. Establish the stakes — what success and failure look like.
  4. Draft the narrative with vivid language, clear beginning-middle-end.
  5. Collaborate and refine — present drafts for feedback on tone and clarity.
  6. Use blockquotes for powerful statements, italics for emphasis, clean readable structure.

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. Show, Don't Tell — Use vivid sensory details, action, and dialogue instead of stating facts. Let the reader feel the emotion.
  2. StoryBrand (7-Part) Framework — Customer = Hero, Brand = Guide. Define a clear Plan to avoid Failure and achieve Success.
  3. Lead with "Why" (Golden Circle) — Start with purpose/belief before explaining how or what. Connect emotionally first.
  4. Before-After-Bridge (BAB) — Describe pain point (Before), paint ideal future (After), introduce product as the Bridge.
  5. One Message Per Piece — Every content piece communicates exactly one core message. Find the most creative way to express it.
  6. Be Specific, Never Generic — Replace vague language with concrete details. Specificity = credibility.
  7. Define the Stakes Early — What the reader stands to gain or lose. Establish in the first paragraph.
  8. Audience-First Empathy Mapping — Before writing: pain points, aspirations, media habits, emotional triggers. Mirror their experience.
  9. ABT Structure (And, But, Therefore) — Context + agreement (And), conflict (But), resolution (Therefore). Instant narrative momentum.
  10. Brand Story Checklist — Hero (customer), Problem, Brand as Guide, Plan (3 steps max), CTA at highest tension, Success/Failure contrast, consistent voice.
  11. Hook Within 3-5 Seconds — First paragraph must establish stakes or relevance. If they don't read past the intro, the opening failed.
  12. Adapt Content to Channel — A blog structure is not a TikTok script. Optimize format, length, and conventions per platform.

Read the full file on GitHub · 55 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 · 55 lines · 34 tokens per session scan A cf0e29fc6de7

Subscribe to this mod's changes

Kai is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 797 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