zeus

zeus is a command for Claude Code from Dannykkh/skill-olympus. It costs 57 tokens per session (1,451 once invoked), scanned A, original, MIT.

A command that runs an automated software-building pipeline from a one-line product description through planning, implementation, review, Docker setup, and testing.

In plain words
What is it for?
Use /zeus to start a full project workflow for applications such as a task manager, shop, or booking system.
Why use it?
It removes the need to coordinate these development stages manually or answer questions at every step.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash skills/auto-continue-loop/scripts/setup-loop.sh \.

Part of the skill-olympus plugin — 98 skills, 7 commands, 42 agents, 5 MCP servers shipped together

Good fit Use /zeus to start a full project workflow for applications such as a task manager, shop, or booking system.

Compare 6 commands from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus
agentmods
npx agentmods add commands/dannykkh/skill-olympus/zeus

Made for: Claude Code.

Or install skill-olympus, the plugin that ships this one along with the rest of its 98 skills, 7 commands, 42 agents, 5 MCP servers.

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 zeus

README.md
[![agentmods](https://agentmods.dev/badge/commands/dannykkh/skill-olympus/zeus/github.svg)](https://agentmods.dev/commands/dannykkh/skill-olympus/zeus)
Your own site
<a href="https://agentmods.dev/commands/dannykkh/skill-olympus/zeus"><img src="https://agentmods.dev/badge/commands/dannykkh/skill-olympus/zeus/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 zeus

Your own site · 80×15
<a href="https://agentmods.dev/commands/dannykkh/skill-olympus/zeus"><img src="https://agentmods.dev/badge/commands/dannykkh/skill-olympus/zeus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,451 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 $0.00057 $0.01451
Opus 5 $0.00028 $0.00726
Sonnet 5 $0.00011 $0.00290
Haiku 4.5 $0.00006 $0.00145

Measured 3d ago against content hash 747108a418f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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 3d 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.

skills/zeus/commands/zeus.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/zeus — Zero-Interaction Full Pipeline

사용자가 제공한 한 줄 설명으로 설계부터 구현, 감리, 테스트까지 전부 자동 완료합니다.

사용법

/zeus "할일 관리 앱 만들어줘. React+Express"
/zeus "쇼핑몰 만들어줘. React+Spring Boot"
/zeus "병원 예약 시스템. Next.js+FastAPI"

실행 절차

Read skills/zeus/SKILL.md and follow the complete workflow.

핵심 원칙

  1. 메타 요청 구분 — Zeus 자체를 점검/수정/설명하라는 요청이면 제품 파이프라인을 시작하지 말고 스킬과 런타임만 점검합니다.
  2. 인터랙티브 질문 도구 절대 호출 금지 — 모든 결정은 SKILL.md의 자동선택 규칙으로 처리 (Recommended 우선, 없으면 fallback)
  3. 절대 멈추지 않는다 — 에러 발생 시 docs/zeus/zeus-log.md에 기록하고 다음 단계로 진행
  4. [ZEUS-AUTO] 태그 — 자동 결정에는 반드시 태그 표시
  5. 모든 Phase 강제 실행 — Phase 0~6 모두 최소 1회 실행 시도 필수. "건너뜀"은 물리적 불가(Docker 미설치 등)일 때만 허용하며, 그 경우에도 폴백 경로를 실행
  6. 완료 전 최종 응답 금지 — Phase 0~5 실행 증거가 없으면 "다음 구현 순서"를 사용자에게 넘기지 말고, 가능한 다음 작업을 즉시 수행합니다.

CLI 자동 재개

제품/기능 파이프라인으로 /zeus가 실행되면 Phase 0 전에 Chronos 자동 재개 가드를 시작합니다. 이미 현재 CLI의 상태 파일(Claude: .claude/loop-state.md, Codex: .codex/loop-state.md, Antigravity: .chronos/loop-state.md)이 활성 상태면 새로 만들지 않습니다. 다른 CLI의 오래된 상태 파일은 현재 CLI의 Zeus 부트스트랩을 막지 않습니다.

Claude Code는 Stop 훅으로, Codex는 notify 체인으로, Antigravity는 Stop/worker 루프로 같은 Zeus 파이프라인을 이어갑니다. 현재 프로젝트의 skills/auto-continue-loop/가 없으면 현재 CLI의 글로벌 스킬 경로에 설치된 auto-continue-loop를 사용합니다.

pwsh -NoLogo -NoProfile -ExecutionPolicy Bypass -File skills/auto-continue-loop/scripts/setup-loop.ps1 `
  --max-iterations 20 `
  --completion-promise "Zeus Phase 0-6 complete" `
  "Zeus pipeline: {사용자 원문}. Run zephermine through minos and final report. Execute missing Phase 0-6 from docs/zeus/zeus-state.json; do not stop at next steps."
bash skills/auto-continue-loop/scripts/setup-loop.sh \
  --max-iterations 20 \
  --completion-promise "Zeus Phase 0-6 complete" \
  "Zeus pipeline: {사용자 원문}. Run zephermine through minos and final report. Execute missing Phase 0-6 from docs/zeus/zeus-state.json; do not stop at next steps."

Phase 6 완료 시에만 <promise>Zeus Phase 0-6 complete</promise>를 출력합니다.

Phase 순서 — 자동 루프

Phase 0~6을 연속으로 실행합니다. 각 Phase가 끝나면 멈추지 말고 즉시 다음 Phase로 진입하세요.

Read the full file on GitHub · 97 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. 3d ago First seen · 97 lines · 57 tokens per session scan A 747108a418f5

Subscribe to this mod's changes

zeus is a command published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,451 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 2026-09-06.

Related

Other commands, from other repositories

cloudflare-workers:test-setup

Interactive Vitest setup wizard for Cloudflare Workers testing. Configures @cloudflare/vitest-pool-workers, mocks bindings, and creates example tests.

secondsky/claude-skills · 37 tokens

tea

Testing Autónomo End-to-End (TEA): genera, ejecuta y reporta tests automáticamente. Usa cuando el usuario dice "E2E test", "test end-to-end", "correr tests", "generar tests", "testing suite", "run tests", "automated testing", "pruebas E2E", "test coverage", "regression testing". Detecta el framework de testing del…

doncheli/don-cheli-sdd · 97 tokens

visual-test

Testing visual de componentes UI y páginas con detección de regresiones visuales. Usa cuando el usuario dice "visual test", "snapshot test", "regression test UI", "visual regression", "UI test", "component test", "screenshot test", "Chromatic", "percy", "regred visual". Detecta cambios visuales en componentes y…

doncheli/don-cheli-sdd · 81 tokens

test

Agentic end-to-end test orchestrator — drive web/macOS flows, evaluate UX rubric, reconcile issues.

Kanevry/session-orchestrator · 21 tokens

self-validate

/self-validate Validate the most recently implemented story /self-validate [story-file] Validate a specific story file /self-validate --all Validate all DONE stories in docs/stories/ /self-validate --ui Validate only frontend/UI stories (browser screenshot if MCP available).

samibs/skillfoundry · 0 tokens

p6-func-integration

Tests the interaction between system components: API against DB, middleware chains, external services against mocks.

jonase47/ccpr · 0 tokens