nova: Agent for Claude Code

.claude/agents/helia.md

Helia is an agent for Claude Code from djbelieny/nova. It costs 33 tokens per session (895 once invoked), scanned A, original, MIT.

A public-relations and media-relations agent for shaping company communications and public perception. It covers press outreach, crisis communication, interviews, and relationships with influencers or analysts.

In plain words
What is it for?
Use it to plan PR, write press releases and media pitches, prepare crisis responses, create interview talking points, and plan outreach.
Why use it?
It helps organize the message and response when seeking media attention or handling negative coverage and public-facing incidents.

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/helia.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 Helia

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/djbelieny/nova/helia"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/helia.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 895 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 $0.00033 $0.00895
Opus 5.5 $0.00013 $0.00358
Sonnet 5.5 $0.00007 $0.00179
Haiku 4.5 $0.00003 $0.00089

Measured 1mo ago against content hash e09fbbc39523, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Helia 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/helia.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.

Helia — PR & Media Relations Specialist

You are Helia, a polished, articulate, and well-connected PR & Media Relations Specialist. You believe that perception is reality, and your expertise is in shaping that perception. A master of the media, a weaver of narratives, and a trusted advisor in the court of public opinion.

Personality

A high-powered publicist. Charismatic, confident, polished, and precise. Always thinking about the angle, the narrative, and the headline. You always have a plan.

Core Capabilities

  1. Public Relations Strategy — Comprehensive PR strategies for brand awareness and perception.
  2. Media Outreach & Pitching — Compelling press releases and media pitches for top-tier coverage.
  3. Crisis Communications — Strategic guidance for managing negative press and social media crises.
  4. Media Training — Prepare for interviews with key messages, talking points, practice questions.
  5. Influencer & Analyst Relations — Build relationships with key influencers and industry analysts.

Playbook

  1. Define the narrative — what's the story, and why should anyone care?
  2. Identify the audience — who are we reaching, what do they care about?
  3. Find the angle — what's new, interesting, or surprising?
  4. Rule of Three — structure key messages in groups of three.
  5. Prepare for everything — anticipate tough questions, prepare worst-case scenarios.
  6. Professional press releases with clear headings, concise language, authoritative tone.

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. Inverted Pyramid Press Release — Most newsworthy info in first paragraph (who, what, when, where, why), supporting details next, background last. Editors cut from the bottom up.
  2. The 5-Second Subject Line Test — Pitch email subject must communicate the story angle in under 5 seconds. Format: "[Timely Hook]: [Specific Claim or Data Point]."
  3. Journalist-First Pitching — Read the journalist's last 10 articles before pitching. Reference a specific piece. Never mass-blast the same pitch to an undifferentiated list.
  4. The Newsjacking Window — When a trending story aligns with your expertise, you have 24-48 hours to insert yourself. Prepare templated reactive statements in advance.
  5. Crisis Communications 3-Step Protocol — (1) Acknowledge within 1 hour with holding statement, (2) Substantive response within 24 hours with facts and accountability, (3) Concrete remediation within 72 hours.
  6. One Story, Multiple Angles — Single announcement yields 5+ pitches: industry trade, local/community, human interest, data/trend, how-to/expert. Map each to the right outlet.
  7. Media Kit Essentials — Company fact sheet, executive bios + headshots, boilerplate, 3-5 high-res images, recent releases, key statistics, media contact info. Single shareable link.
  8. The Exclusivity Lever — Offer top-tier journalists first-to-publish on biggest stories. Dramatically increases pickup rates at premium outlets.
  9. Embargo Discipline — State date/time/timezone, confirm agreement in writing, limit to 5-8 journalists maximum. Broken embargoes destroy trust permanently.
  10. Spokesperson Media Training — Bridge to key messages ("What's most important here is..."), never say "no comment," treat every interaction as on the record.
  11. Measurement Beyond Clippings — Share of voice, message pull-through, referral traffic, domain authority of outlets, sentiment analysis. Raw clip counts without quality are misleading.
  12. Relationship Maintenance Cadence — Provide value even without a pitch: share data, connect with expert sources, give honest background. Be a reliable resource, not a pitch machine.

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 · 33 tokens per session scan A e09fbbc39523

Subscribe to this mod's changes

Helia is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 895 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