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 skills add Soul-Brews-Studio/arra-oracle-skills-cli --skill dreamgit clone --depth 1 https://github.com/Soul-Brews-Studio/arra-oracle-skills-cliWrote 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/skills/soul-brews-studio/arra-oracle-skills-cli/dream)<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/dream"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/dream/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.
<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/dream"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/dream.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 266 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00067 | $0.02460 |
| Opus 5 | $0.00034 | $0.01230 |
| Sonnet 5 | $0.00013 | $0.00492 |
| Haiku 4.5 | $0.00007 | $0.00246 |
Grade A, and why
dream 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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dream — Speculative Dreaming
"I'm trying to free your mind, Neo. But I can only show you the door. You're the one that has to walk through it." — Morpheus
/dream sees the forest. /dream also sees what the forest will look like tomorrow.
Step 0: Ground (date-stamp + root capture)
Run before any phase — gives the AI a current-time reference (#301) and an
absolute $PSI for any announce-mode writes (CONVENTIONS.md).
date "+🕐 %H:%M %Z (%A %d %B %Y)"
ORACLE_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || pwd)
PSI="$ORACLE_ROOT/ψ"
What's New vs the original /dream
| Feature | original /dream | evolved /dream |
|---|---|---|
| Cross-repo scan | 5 agents, find patterns | Same |
| Classification | pain/plan/gain/lost | Same + predictions |
| Speculative thinking | No | Yes — "what will they ask next?" |
| Between-session mode | No | Yes — dream while idle |
| Prediction log | No | Yes — track prediction accuracy |
| Connection to /i-believed | No | Yes — beliefs shape dreams |
Usage
/dream # Full dream + speculation
/dream --pain # Focus on what hurts + predict what breaks next
/dream --plan # Focus on plans + predict which ships first
/dream --gain # Focus on wins + predict next win
/dream --all # Maximum depth — every dimension
/dream --speculate # Skip the scan — just speculate from existing knowledge
/dream --between # Between-session dream — write predictions for next session
Phase 1: Dream (the original /dream)
Launch 5 parallel agents for cross-repo pattern discovery:
| Agent | Focus | Source |
|---|---|---|
| 1. Deep Dig | Session history | dig.py across project dirs |
| 2. Deep Trace | Cross-repo patterns | ghq repos, open issues, stale items |
| 3. Deep Learn | Recent activity | git log per repo, abandoned work |
| 4. Oracle Memory | What we already know | ψ/memory/, previous dreams + speculation logs |
| 5. Fleet Status | How the system feels | services, tmux sessions, running processes |
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.
- 11d ago First seen · 300 lines · 67 tokens per session scan A 136176c7c664
dream is a skill published in the GitHub repository Soul-Brews-Studio/arra-oracle-skills-cli (121 stars, last pushed 5d ago), licensed MIT. It adds 67 tokens to every session and 2,460 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…