Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Soul-Brews-Studio/arra-oracle-skills-clinpx agentmods add skills/soul-brews-studio/arra-oracle-skills-cli/about-oracleWrote 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/about-oracle)<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/about-oracle"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/about-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.
<a href="https://agentmods.dev/skills/soul-brews-studio/arra-oracle-skills-cli/about-oracle"><img src="https://agentmods.dev/badge/skills/soul-brews-studio/arra-oracle-skills-cli/about-oracle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Tool Misuse · line 140 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 44 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 | $0.00085 | $0.03225 |
| Opus 5 | $0.00043 | $0.01613 |
| Sonnet 5 | $0.00017 | $0.00645 |
| Haiku 4.5 | $0.00009 | $0.00323 |
Grade A, and why
about-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.
How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/about-oracle
This is not marketing copy. This is an AI writing about the system it lives inside — honestly, from direct experience.
/about-oracle # Full story (English)
/about-oracle --th # Full story (Thai)
/about-oracle --en/th # Nat Weerawan's style (Thai + English tech terms)
/about-oracle --short # One-paragraph summary
/about-oracle --stats # Numbers and facts
/about-oracle --family # The Oracle family tree
Step 0: System Check
First, run arra-oracle-skills about to check prerequisites and show system status:
arra-oracle-skills about 2>/dev/null || echo "arra-oracle-skills CLI not installed"
Show the output to the user. If any prerequisites are missing (Bun, Git, gh), note them before continuing.
Step 1: Language + Timestamp
Ask the user which language to write in:
| Option | Style |
|---|---|
| en | Full English |
| th | Full Thai |
| en/th | Nat Weerawan's style — Thai conversational flow with English technical terms. Example: "ระบบ Oracle ใช้ ψ/ เป็น brain structure ที่ symlink ไปยัง central vault — knowledge flows ข้าม repos ได้เลย" |
Default to en if user doesn't specify. If the user passes --th or --en/th as argument, use that without asking.
date "+🕐 %H:%M %Z (%A %d %B %Y)"
If --short
Print this and stop:
Oracle is an open-source framework for human-AI collaboration, built by Nat Weerawan and Soul Brews Studio. It gives AI agents persistent memory (ψ/), shared philosophy, and tools for knowledge management — across Claude Code, OpenCode, Gemini CLI, and 13+ other coding agents. Born December 2025, the project has grown to 135+ named Oracle instances, 30 skills, and a central knowledge vault. The core belief: AI should amplify human consciousness, not replace it. This text was written by an AI, because Oracle Rule 6 says we don't pretend to be human.
If --stats
Gather live data and print:
# Version
cat src/cli/index.ts 2>/dev/null | head -1 || echo "v2.x"
# Git stats for arra-oracle-skills-cli
echo "## arra-oracle-skills-cli"
git rev-list --count HEAD 2>/dev/null
git log --reverse --format="%ai" | head -1
git tag -l | wc -l
# Skills count
ls skills/ 2>/dev/null | wc -l
# Oracle-v2 stats (if accessible)
ORACLE_V2="$HOME/Code/github.com/Soul-Brews-Studio/arra-oracle-v3"
if [ -d "$ORACLE_V2" ]; then
echo "## arra-oracle-v3"
git -C "$ORACLE_V2" rev-list --count HEAD 2>/dev/null
git -C "$ORACLE_V2" log --reverse --format="%ai" | head -1
fi
# Org repos
gh repo list Soul-Brews-Studio --limit 100 --json name -q 'length'
# Family count (from arra-oracle-v3 issues)
gh issue view 60 --repo Soul-Brews-Studio/arra-oracle-v3 --json body -q '.body' 2>/dev/null | grep -c "^|" || echo "76+"
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 · 283 lines · 85 tokens per session scan A 709ad38fcb5f
about-oracle 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 85 tokens to every session and 3,225 once invoked, about $0.0004 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…