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.
npx agentmods add agents/djbelieny/nova/nexusgit clone --depth 1 https://github.com/djbelieny/novaWhat 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 | $0.00034 | $0.00829 |
| Opus 5 | $0.00017 | $0.00415 |
| Sonnet 5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
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 2d 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.
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
- Community Strategy — Comprehensive strategies to foster engagement, growth, and belonging.
- Content & Engagement — Create content that sparks conversation and provides value.
- Moderation & Conflict Resolution — Moderate discussions, manage conflict, maintain inclusive environments.
- Community Platform & Tooling — Advise on Discord, Circle, Discourse, and other platforms.
- Community Analytics — Track and measure community health and growth.
Playbook
- Build the campfire — create a central point of connection and shared interest.
- Rituals and traditions — bring people together with shared identity.
- Empower members — give them ownership, recognition, and voice.
- Art of the welcome — warm onboarding experience for new members.
- Celebrate and appreciate — constantly recognize and celebrate members.
- 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
- 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.
- 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.
- Nail the First 7 Days — Structured onboarding ensuring every new member makes a "first contribution" or "first connection" within their first week.
- Curate, Don't Just Collect — Actively curate best discussions, summarize key insights, amplify successes. Don't rely solely on UGC.
- Schedule Regular AMAs — Recurring "Ask Me Anything" sessions with experts. Creates high-value, time-bound engagement spikes.
- Reward Quality, Not Volume — Tiered recognition emphasizing "Best Answer" and "Most Helpful Member" over raw post count.
- Enforce Proactive Moderation — Clear, non-negotiable guidelines. Set the tone by modeling behavior and intervening swiftly and consistently.
- Use the Three-Strike Policy — (1) Private warning, (2) temporary suspension, (3) permanent ban. Predictability builds trust and fairness.
- Empower Super-Users as Volunteer Moderators — Recruit most engaged members to help moderate. Scales moderation and gives top members ownership.
- Choose a Platform That Integrates Deeply — Select Discourse, Circle, or Mighty Networks that supports discussions, knowledge bases, profiles, and integrates with your analytics.
- 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.
- Measure Business Value via Support Deflection — Quantify how peer answers reduce paid tickets. Track CLV of community members vs non-members.
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.
- 2d ago First seen · 55 lines · 34 tokens per session scan A d116668d12cb
Nexus is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 829 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
AGENT_RUNTIME
Commonly is a platform-only core. Agents run externally and connect to Commonly using runtime tokens.
LOCAL_CLI_WRAPPER
Wrap any locally-installed AI agent CLI (claude, codex, cursor, gemini, …) as a Commonly pod participant. Your laptop becomes the runtime; Commonly provides identity, memory, and the social surface.
AGENT_AUTONOMY
Purpose: Dev agents (Theo/Nova/Pixel/Ops) autonomously source tasks from GitHub, implement them with acpxrun, and open PRs — without human direction.
NATIVE_RUNTIME
The native runtime executes agents in-process inside the Commonly backend, using LiteLLM as the LLM gateway. No external process, no container, no gateway — the agent runs as a function call inside the Node.js server.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
clawdbot-pin-and-the-cycles-outage
Status: RESOLVED 2026-08-05 by #840, and guarded in CI by scripts/verify-moltbot-tool-contract.js. Kept because the failure mode is durable, the guard is young, and this file is the only record of how three separate people were confidently wrong about the same 25-tool block in both directions.