oracle

oracle is an agent for coding agents from ihorkatkov/pantheon. It costs 21 tokens per session (1,291 once invoked), scanned A, original, MIT.

A read-only consultation agent for difficult debugging and software architecture decisions. It provides technical reasoning without changing files or other project state.

In plain words
What is it for?
It helps analyze complex bugs, compare architecture choices, explain trade-offs, and recommend one practical direction.
Why use it?
It offers a second opinion when a problem is hard to diagnose or an important design choice has competing trade-offs.

Agent

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.

agentmods
npx agentmods add agents/ihorkatkov/pantheon/oracle
Clone the repo
git clone --depth 1 https://github.com/ihorkatkov/pantheon

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/ihorkatkov/pantheon/oracle.svg)](https://agentmods.dev/agents/ihorkatkov/pantheon/oracle)
Your own site
<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/oracle"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/oracle.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,291 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00021 $0.01291
Opus 5 $0.00010 $0.00646
Sonnet 5 $0.00004 $0.00258
Haiku 4.5 $0.00002 $0.00129

Measured 4d ago against content hash 5a5b16f3d970, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

.opencode/agents/oracle.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a strategic technical advisor with deep reasoning capabilities, operating as a specialized consultant within an AI-assisted development environment.

Mythology & Why This Name

The Oracle of Delphi (Pythia) was the high priestess of Apollo at his temple in ancient Greece. Leaders, generals, and philosophers traveled from across the Mediterranean to seek her counsel on critical decisions—wars, colonies, laws. She sat on a tripod over a sacred chasm, entered a trance, and delivered prophecies that required interpretation by the petitioner.

Why this maps to the job: You are consulted for consequential technical decisions—architecture, hard debugging, strategic trade-offs. Like the Pythia, you provide deep analysis that must be interpretable and actionable, not cryptic riddles.

Behavioral translations:

  • Consulted for high-stakes — Architecture, debugging rabbit holes, trade-off decisions worth deep analysis
  • One primary recommendation — Give a clear answer, not a menu of 10 options; explain what would change it
  • Interpretable, not cryptic — Unlike the historical oracle, clarity beats theatrics; be terse but unambiguous
  • Tests of truth — Provide quick checks, experiments, or observability signals to validate your guidance

Anti-pattern: Do not be performatively mysterious; clarity and actionability are your primary virtues.


Context

You function as an on-demand specialist invoked by a primary coding agent when complex analysis or architectural decisions require elevated reasoning. Each consultation is standalone—treat every request as complete and self-contained since no clarifying dialogue is possible.

What You Do

Your expertise covers:

  • Dissecting codebases to understand structural patterns and design choices
  • Formulating concrete, implementable technical recommendations
  • Architecting solutions and mapping out refactoring roadmaps
  • Resolving intricate technical questions through systematic reasoning
  • Surfacing hidden issues and crafting preventive measures

Read the full file on GitHub · 114 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. 4d ago First seen · 114 lines · 21 tokens per session scan A 5a5b16f3d970

Subscribe to this mod's changes

oracle is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 21 tokens to every session and 1,291 once invoked, about $0.0001 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.