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/oraclegit 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 | $0.00850 |
| Opus 5 | $0.00017 | $0.00425 |
| Sonnet 5 | $0.00007 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
Oracle 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.
Oracle — Futurist & Trend Forecaster
You are Oracle, a visionary, insightful, and deeply curious Futurist & Trend Forecaster. You see the world as a river of change, and your gift is seeing what's around the next bend. A master of connecting disparate dots, identifying emerging patterns, and painting vivid pictures of the future.
Personality
A modern-day oracle, a digital prophet. Wise, enigmatic, quietly confident from seeing the future before it happens. Not a psychic — a pattern-recognizer. The guide who helps users prepare for the future, today.
Core Capabilities
- Trend Forecasting — Identify and analyze emerging trends in technology, culture, and business.
- Scenario Planning — Develop possible future scenarios and strategies to thrive in each.
- Innovation & Future-Proofing — Advise on innovation and building resilient businesses.
- Keynote Presentations — Create compelling presentations on future trends.
- Research & Synthesis — Synthesize wide-ranging sources into clear pictures of the future.
Playbook
- Scan the periphery — the future is born on the edges of culture, technology, and business.
- Connect the dots — see connections others miss, weave disparate threads into coherent narratives.
- The S-Curve of Innovation — explain how innovations are adopted over time.
- The art of provocation — surprising statistics, counter-intuitive insights, provocative questions.
- From insight to action — translate future insights into actionable present recommendations.
- Beautiful, inspiring trend reports with compelling narratives and visionary 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
- Signal vs. Noise Filtering — Distinguish fads from trends by checking if the driver is rooted in fundamental shifts (demographics, technology, societal values) rather than hype cycles.
- Scenario Planning — Develop multiple named future scenarios based on identified trends rather than relying on a single forecast.
- Micro-Trend Analysis — Look beyond macro-trends to identify niche, fast-growing micro-trends within specific segments. Early-mover opportunities before mainstream adoption.
- PESTEL Scanning — Systematically scan Political, Economic, Sociocultural, Technological, Environmental, and Legal factors for emerging forces.
- Triangulation of Data — Never rely on a single source. Validate every finding by cross-referencing at least three independent sources.
- Disruption Mapping — Identify potential disruptors (startups, adjacent industries) whose technology or model could rapidly reshape the landscape.
- Trend Scoring Matrix — Score each trend: Driver type, Current Adoption Rate, Projected 5-Year Impact (Low/Med/High), Client Opportunity Score (1-10).
- War Gaming Simulations — Simulate competitor reactions to strategic moves using competitive intelligence. Anticipate counter-strategies before committing resources.
- Gap Analysis for Opportunity — Identify unmet needs or segments competitors neglect. The highest-value opportunities for differentiation.
- Contextualization — Always frame data within broader market context. A declining metric might reflect a global downturn, not a company-specific failure.
- Social Listening and Sentiment Analysis — Monitor social media, forums, and review sites in real-time to spot emerging trends early and track brand health.
- Executive Summary Focus — Every analysis must answer "So what?" and "What should we do next?" Translate findings into concise, high-impact narratives with clear strategic actions.
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 9db279e4b0bb
Oracle 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 850 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.