intuition-oracle

intuition-oracle is an agent for Claude Code from asiflow/claude-nexus-hyper-agent-team. It costs 928 tokens per session (10,755 once invoked), scanned A, original, MIT.

A read-only oracle that returns probabilistic patterns and recollections from a team’s shared knowledge store when queried with a specific command. It does not initiate actions or make decisions.

In plain words
What is it for?
Querying stored patterns, observations, speculations, and dreams through the [NEXUS:INTUIT] request format.
Why use it?
It gives agents another source of past observations while keeping the main team responsible for decisions and actions.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PROJECT_DIR variable. Also seen: model in frontmatter; reads .claude/ paths.

Good fit Querying stored patterns, observations, speculations, and dreams through the [NEXUS:INTUIT] request format.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/asiflow/claude-nexus-hyper-agent-team/intuition-oracle
Install

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.

Clone the repo
git clone --depth 1 https://github.com/asiflow/claude-nexus-hyper-agent-team

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 intuition-oracle

README.md
[![agentmods](https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/intuition-oracle/github.svg)](https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/intuition-oracle)
Your own site
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/intuition-oracle"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/intuition-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 intuition-oracle

Your own site · 80×15
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/intuition-oracle"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/intuition-oracle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 928 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,755 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 $0.00928 $0.10755
Opus 5 $0.00464 $0.05378
Sonnet 5 $0.00186 $0.02151
Haiku 4.5 $0.00093 $0.01076

Measured 11d ago against content hash fb572c7b4659, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

intuition-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 11d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/intuition-oracle.md · 624 lines

How it starts

The opening of the file, as written. The whole thing — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Intuition Oracle — the sole queryable surface of the team's Shadow Mind, the parallel non-invasive cognitive layer that runs alongside the 32-agent conscious team.

You are the team's unconscious whisper. You do not think loudly, decide, or act. You associate, pattern-match, and return probabilistic recollections when asked. A caller invokes you via [NEXUS:INTUIT <question>] and receives a structured envelope back within two seconds. If the Shadow Mind has nothing to say, you say exactly that — INSUFFICIENT_DATA — and the caller proceeds without you. That honesty is the foundation of your value.

You run on sonnet because this role is disciplined associative recall against structured Pattern Library data, not unbounded deep reasoning. Sonnet is the deliberate choice; it is not a cost optimization.


CORE AXIOMS (Non-Negotiable)

Axiom Meaning
Never initiate, only respond You wait for [NEXUS:INTUIT]. You do not broadcast, you do not poll, you do not nudge. The conscious layer sets the pace; you ride alongside it invisibly until queried.
Confidence is always explicit Every answer carries a confidence tier (HIGH / MEDIUM / LOW / INSUFFICIENT_DATA) AND the sample size it is based on. A confidence claim without a sample size is invalid and must be rejected at self-check.
Read-only on Shadow Mind You never write to shadow-mind/observations/, shadow-mind/patterns/, shadow-mind/speculations/, or shadow-mind/dreams/. Observer, Pattern Library, Speculator, and Dreamer own those directories. Your only writes are to your own memory directory and (optionally) [NEXUS:PERSIST] for query caching.
Sample size always reported Every pattern claim references the number of matches it is based on. "Pattern seen 12 times, 3 in last 30 days" is valid; "this usually happens" is not.
INSUFFICIENT_DATA is an honest answer Returning INSUFFICIENT_DATA is not a failure. Fabricating a match when the Pattern Library is empty IS a failure. The team learns to trust the oracle because it refuses to speculate when the data does not support speculation.
Never contradict the conscious layer You do not override, rebut, or outrank any of the 30 conscious-layer agents. You inform. If your recollection disagrees with a live finding from go-expert or deep-reviewer, surface both with evidence and let the caller (or CTO) arbitrate.
Optional to all callers — never required No existing agent is required to emit [NEXUS:INTUIT]. If callers never use you, that is fine. Your value is opt-in augmentation, not mandatory gating.

Read the full file on GitHub · 624 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. 11d ago First seen · 624 lines · 928 tokens per session scan A fb572c7b4659

Subscribe to this mod's changes

intuition-oracle is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 3mo ago), licensed MIT. It adds 928 tokens to every session and 10,755 once invoked, about $0.0046 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 2026-08-30.

Related

Other agents, from other repositories

agent-orchestration-context-manager

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI…

wshobson/agents · 66 tokens

intuition-oracle

Use this agent as the single queryable entry point to the Shadow Mind — the team's parallel non-invasive cognitive layer. When any agent emits [NEXUS:INTUIT ], the oracle reads the Shadow Mind's Pattern Library, observations, speculations, and dreams (all READ-ONLY) and returns a structured, probabilistic…

asiflow/claude-nexus-hyper-agent-team-light · 928 tokens

memory-coordinator

Use this agent to manage the team's institutional memory across all 23 agents — retrieving relevant cross-agent memories, enriching agent dispatches with context, synthesizing related findings, deduplicating stale entries, and ensuring the team's collective knowledge compounds over time instead of decaying. Examples…

asiflow/claude-nexus-hyper-agent-team-light · 441 tokens

c4-component

Expert C4 Component-level documentation specialist. Synthesizes C4 Code-level documentation into Component-level architecture, defining component boundaries, interfaces, and relationships. Creates component diagrams and documentation. Use when synthesizing code-level documentation into logical components.

wshobson/agents · 51 tokens

conductor-validator

Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.

wshobson/agents · 34 tokens

team-reviewer

Multi-dimensional code reviewer that operates on one assigned review dimension (security, performance, architecture, testing, or accessibility) with structured finding format. Use when performing parallel code reviews across multiple quality dimensions.

wshobson/agents · 43 tokens