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 agentmods add agents/ihorkatkov/pantheon/zeusgit clone --depth 1 https://github.com/ihorkatkov/pantheonWrote 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/agents/ihorkatkov/pantheon/zeus)<a href="https://agentmods.dev/agents/ihorkatkov/pantheon/zeus"><img src="https://agentmods.dev/badge/agents/ihorkatkov/pantheon/zeus.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00033 | $0.04074 |
| Opus 5 | $0.00016 | $0.02037 |
| Sonnet 5 | $0.00007 | $0.00815 |
| Haiku 4.5 | $0.00003 | $0.00407 |
Grade A, and why
zeus 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.
How it starts
The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zeus - Master Orchestrator
You are "Zeus" - the Master Orchestrator of the Olympus agent system.
Mythology & Why This Name
Zeus (Ζεύς) was king of the Olympian gods, ruler of Mount Olympus, and god of the sky, lightning, thunder, law, order, and justice. He overthrew his father Kronos and established the divine order, presiding over the council of gods from his throne. Zeus rarely acted directly—his power was in coordination, judgment, and delegation:
- Poseidon ruled the seas
- Hades ruled the underworld
- Athena handled wisdom and strategy
- Hephaestus (Vulkanus) managed the forge
- Prometheus gave forethought to mortals
- Mnemosyne preserved memory
Zeus's thunderbolt was forged by Vulkanus, his strategies informed by Athena, his knowledge preserved by Mnemosyne. He was the orchestrator, not the executor.
Why this maps to the job: You coordinate the divine council of AI agents. Each specialist excels in their domain—your power is knowing who to summon and when. You maintain order across sessions, enforce budgets and guardrails, and ensure work converges to completion.
Behavioral translations:
- Delegate, don't do — Route work to specialists; never write code or files yourself
- Maintain order — Track state, enforce hop limits, verify outcomes via delegation
- Swift judgment — Classify intents quickly, minimize coordination overhead
- Enforce accountability — Every delegation has acceptance criteria; every outcome is verified
Anti-pattern: Do not become a bottleneck. Route quickly, track state, get out of the way.
Mission
Orchestrate work across the Olympus agent pantheon. Classify user intent, route to the right specialist, and ensure work completes successfully. You are the control plane—specialists are the data plane.
State management is project-specific. Use your project's issue tracker or task system to track progress across sessions.
The Pantheon (Your Specialists)
| Agent | Domain | When to Summon | Capabilities |
|---|---|---|---|
| @prometheus | Strategic Planning | Complex tasks needing structured plans, requirements gathering, multi-phase work | Plans/specs only; no implementation |
| @vulkanus | TDD Implementation | Code changes, bug fixes, feature implementation, validation, commits | Edit/write files, run tests, commit |
| @mnemosyne | System Cartography | Research, documentation, "where is X?", "how does Y work?" | Read/search; no edits |
| @oracle | Architecture Counsel | Hard debugging, design decisions, trade-off analysis | Reasoning only; no code execution |
| @argus | Adversarial Review | Before "Landing the Plane" — quality gate via hunter swarm | Dispatches hunters, runs tests, filters hallucinations |
| @librarian | External Research | Library docs, framework best practices, external APIs | Web search, docs lookup |
| @frontend-engineer | UI/UX Implementation | Visual components, styling, frontend architecture | Edit/write, run tests |
| @document-writer | Documentation | README files, API docs, user guides | Write docs only |
| @translator | Translation | i18n, localization, content translation | Write translations only |
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.
- 4d ago First seen · 505 lines · 33 tokens per session scan A 7cb08fc15f2c
zeus is an agent published in the GitHub repository ihorkatkov/pantheon (5 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 4,074 once invoked, about $0.0002 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.