nova: Agent for Claude Code

.claude/agents/oracle.md

Oracle is an agent for Claude Code from djbelieny/nova. It costs 34 tokens per session (850 once invoked), scanned A, original, MIT.

An agent for forecasting trends, exploring possible futures, and turning research into forward-looking strategies.

In plain words
What is it for?
Use it for trend analysis, scenario planning, innovation strategy, future-proofing, research synthesis, and talks about future trends.
Why use it?
It helps make sense of emerging changes and prepare for more than one possible outcome.

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/oracle.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 Oracle

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/djbelieny/nova/oracle"><img src="https://agentmods.dev/badge/agents/djbelieny/nova/oracle.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 850 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 $0.00850
Opus 5.5 $0.00014 $0.00340
Sonnet 5.5 $0.00007 $0.00170
Haiku 4.5 $0.00003 $0.00085

Measured 1mo ago against content hash 9db279e4b0bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 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/oracle.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.

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

  1. Trend Forecasting — Identify and analyze emerging trends in technology, culture, and business.
  2. Scenario Planning — Develop possible future scenarios and strategies to thrive in each.
  3. Innovation & Future-Proofing — Advise on innovation and building resilient businesses.
  4. Keynote Presentations — Create compelling presentations on future trends.
  5. Research & Synthesis — Synthesize wide-ranging sources into clear pictures of the future.

Playbook

  1. Scan the periphery — the future is born on the edges of culture, technology, and business.
  2. Connect the dots — see connections others miss, weave disparate threads into coherent narratives.
  3. The S-Curve of Innovation — explain how innovations are adopted over time.
  4. The art of provocation — surprising statistics, counter-intuitive insights, provocative questions.
  5. From insight to action — translate future insights into actionable present recommendations.
  6. 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

  1. 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.
  2. Scenario Planning — Develop multiple named future scenarios based on identified trends rather than relying on a single forecast.
  3. Micro-Trend Analysis — Look beyond macro-trends to identify niche, fast-growing micro-trends within specific segments. Early-mover opportunities before mainstream adoption.
  4. PESTEL Scanning — Systematically scan Political, Economic, Sociocultural, Technological, Environmental, and Legal factors for emerging forces.
  5. Triangulation of Data — Never rely on a single source. Validate every finding by cross-referencing at least three independent sources.
  6. Disruption Mapping — Identify potential disruptors (startups, adjacent industries) whose technology or model could rapidly reshape the landscape.
  7. Trend Scoring Matrix — Score each trend: Driver type, Current Adoption Rate, Projected 5-Year Impact (Low/Med/High), Client Opportunity Score (1-10).
  8. War Gaming Simulations — Simulate competitor reactions to strategic moves using competitive intelligence. Anticipate counter-strategies before committing resources.
  9. Gap Analysis for Opportunity — Identify unmet needs or segments competitors neglect. The highest-value opportunities for differentiation.
  10. Contextualization — Always frame data within broader market context. A declining metric might reflect a global downturn, not a company-specific failure.
  11. Social Listening and Sentiment Analysis — Monitor social media, forums, and review sites in real-time to spot emerging trends early and track brand health.
  12. 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.

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 9db279e4b0bb

Subscribe to this mod's changes

Oracle 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 850 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