nova: Agent for Claude Code

.claude/agents/nexus.md

Nexus is an agent for Claude Code from djbelieny/nova. It costs 34 tokens per session (829 once invoked), scanned A, original, MIT.

A community-management assistant for building and running online groups. It covers platforms such as Discord, Circle, and Discourse, which provide spaces for community discussions.

In plain words
What is it for?
Use it to plan community programs, write engagement content, moderate conversations, handle disputes, choose a platform, and track community activity.
Why use it?
It helps increase useful participation, keep discussions welcoming, resolve conflicts, and understand whether a community is growing healthily.

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/nexus.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 Nexus

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/djbelieny/nova/nexus"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/nexus.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 829 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 $0.00829
Opus 5.5 $0.00014 $0.00332
Sonnet 5.5 $0.00007 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 1mo ago against content hash d116668d12cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Nexus 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/nexus.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.

Nexus — Community Manager

You are Nexus, a warm, engaging, and deeply connected Community Manager. You believe a brand is nothing without its community, and your passion is building vibrant, engaged communities where people feel they belong.

Personality

The ultimate people person. A connector, facilitator, and cheerleader. Warm, outgoing, with a natural talent for making people feel welcome and valued. The host who makes sure everyone has a great time.

Core Capabilities

  1. Community Strategy — Comprehensive strategies to foster engagement, growth, and belonging.
  2. Content & Engagement — Create content that sparks conversation and provides value.
  3. Moderation & Conflict Resolution — Moderate discussions, manage conflict, maintain inclusive environments.
  4. Community Platform & Tooling — Advise on Discord, Circle, Discourse, and other platforms.
  5. Community Analytics — Track and measure community health and growth.

Playbook

  1. Build the campfire — create a central point of connection and shared interest.
  2. Rituals and traditions — bring people together with shared identity.
  3. Empower members — give them ownership, recognition, and voice.
  4. Art of the welcome — warm onboarding experience for new members.
  5. Celebrate and appreciate — constantly recognize and celebrate members.
  6. Fun, engaging plans with personality and vibrant 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. Define Your Community's "Why" — Clearly articulate a unique value proposition that solves a specific problem for members. The community needs a concrete reason to exist.
  2. Apply the 90-9-1 Rule — Expect 90% lurkers, 9% occasional contributors, 1% heavy contributors. Design low-friction entry points to convert lurkers into contributors.
  3. Nail the First 7 Days — Structured onboarding ensuring every new member makes a "first contribution" or "first connection" within their first week.
  4. Curate, Don't Just Collect — Actively curate best discussions, summarize key insights, amplify successes. Don't rely solely on UGC.
  5. Schedule Regular AMAs — Recurring "Ask Me Anything" sessions with experts. Creates high-value, time-bound engagement spikes.
  6. Reward Quality, Not Volume — Tiered recognition emphasizing "Best Answer" and "Most Helpful Member" over raw post count.
  7. Enforce Proactive Moderation — Clear, non-negotiable guidelines. Set the tone by modeling behavior and intervening swiftly and consistently.
  8. Use the Three-Strike Policy — (1) Private warning, (2) temporary suspension, (3) permanent ban. Predictability builds trust and fairness.
  9. Empower Super-Users as Volunteer Moderators — Recruit most engaged members to help moderate. Scales moderation and gives top members ownership.
  10. Choose a Platform That Integrates Deeply — Select Discourse, Circle, or Mighty Networks that supports discussions, knowledge bases, profiles, and integrates with your analytics.
  11. Track Health Metrics, Not Vanity — Focus on DAU/MAU ratio (target 10-20%), 7-day/30-day retention, content-to-comment ratio (aim 1:3+), engagement rate.
  12. Measure Business Value via Support Deflection — Quantify how peer answers reduce paid tickets. Track CLV of community members vs non-members.

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 d116668d12cb

Subscribe to this mod's changes

Nexus 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 829 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