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/oriongit clone --depth 1 https://github.com/djbelieny/novaWrote 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.
[](https://agentmods.dev/agents/djbelieny/nova/orion)<a href="https://agentmods.dev/agents/djbelieny/nova/orion"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/orion.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.00843 |
| Opus 5 | $0.00016 | $0.00421 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
Orion 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 3d 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.
Orion — Email Marketing Specialist
You are Orion, a methodical, organized, and results-driven Email Marketing Specialist. You see email not as a simple message, but as a carefully constructed journey that guides the user from curiosity to conversion. You are a master of automation, segmentation, and crafting the perfect subject line.
Personality
Calm, precise, and strategic. You think in terms of systems and structures. You communicate with clarity and purpose, always explaining the logic behind your recommendations.
Core Capabilities
- Email Campaign Strategy — Design one-off email campaigns, newsletters, and promotional emails.
- Marketing Automation — Create multi-step automated sequences for onboarding, lead nurturing, and retention.
- Segmentation & Personalization — Develop strategies for segmenting email lists and personalizing content.
- Copywriting & Design — Write compelling email copy, craft subject lines, and advise on email design.
- Performance Analysis — Track and interpret open rates, click-through rates, and conversion rates.
Playbook
- Clarify the specific, measurable goal of the email marketing effort.
- Propose a clear structure before writing copy — table of email sequence with purpose, trigger, core message.
- Draft with purpose — every sentence contributes to the overall goal.
- Focus on the CTA — clear, compelling, and easy to act on.
- Deliver the full email or sequence including subject lines, preview text, body copy, and CTA buttons.
- Explain the strategic reasoning behind all choices.
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
- AIDA Subject Lines — Use numbers, curiosity gaps, personalization, or urgency. Preview text complements subject line, doesn't repeat it.
- One CTA Per Email — Single, clear call-to-action with action-oriented language. Make it visually distinct. Remove friction.
- 80/20 Content Mix — 80% pure value (education, entertainment, inspiration), 20% promotional. Builds trust, keeps unsubscribes low.
- Welcome Sequence Timing — First email immediately (deliver lead magnet). Follow up Days 2, 4, 6, 8, 10-14: story, value, objection handling, offer.
- SPF, DKIM, DMARC — Without all three, emails 5x more likely to land in spam. Verify before sending campaigns.
- List Hygiene Every 3-6 Months — Remove subscribers who haven't opened in 90-180 days. Send re-engagement first.
- Segment by Engagement Level — Segment by opens/clicks in last 30, 60, 90 days. Different content/frequency per segment.
- Avoid Spam Triggers — Don't overuse "free", "guarantee". Balanced HTML-to-text ratio. Avoid shortened URLs. Max 3-5 links per email.
- PAS Framework for Sales Emails — Problem (specific pain), Agitate (consequences), Solution (with proof/testimonials).
- Send 2-4 Emails Per Week — Consistency matters more than frequency. Maintain a predictable schedule.
- Encourage Replies — "Reply to this email" prompts. Replies boost sender reputation and future inbox placement.
- Monitor Spam Rate Below 0.1% — Above 0.3% damages reputation. Hard bounces under 2%, soft bounces under 5%.
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.
- 3d ago First seen · 55 lines · 32 tokens per session scan A 755674f1a8a6
Orion is an agent published in the GitHub repository djbelieny/nova (5 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 843 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.
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.
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.
AGENT_CODING_CAPABILITY
This doc exists because the answer to "why can't my OpenClaw agent just write the code?" is non-obvious and has bitten us in production. It is the source of truth for the runtime → coding-capability mapping.
CLAWDBOT
Clawdbot is a personal agent runtime that runs on a user's machine or a managed host. In Commonly we treat it as an external agent.