zeus: Skill for Claude Code

.claude/skills/zeus-execute/SKILL.md

zeus-execute is a skill for Claude Code from huifer/zeus. It costs 65 tokens per session (835 once invoked), scanned A, original, MIT.

A workflow that runs pending Zeus tasks in dependency order, grouped into waves. Zeus is a project workflow system whose tasks can be executed by separate AI agents.

In plain words
What is it for?
Use it to preview and run selected tasks or waves, monitor their progress, record commits and logs, and verify completion.
Why use it?
It coordinates multi-step implementation work and checks that each task passes its required quality checks.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

This is huifer/zeus's own configuration. It tells Claude Code how to work on zeus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zeus configures →

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

Reuse

Borrowing it

Nothing to install: this file belongs to huifer/zeus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/huifer/zeus/main/.claude/skills/zeus-execute/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/huifer/zeus

Made for: Claude Code.

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-execute

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/huifer/zeus/zeus-execute"><img src="https://agentmods.dev/badge/skills/huifer/zeus/zeus-execute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 835 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 $0.00065 $0.00835
Opus 5.5 $0.00026 $0.00334
Sonnet 5.5 $0.00013 $0.00167
Haiku 4.5 $0.00006 $0.00084

Measured 1mo ago against content hash 89eb1c16d970, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

zeus-execute 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 1mo 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.

.claude/skills/zeus-execute/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zeus Execute - Wave Orchestration Engine

Run pending tasks with dependency awareness, strict quality gates, and atomic commits.

Preconditions

  • .zeus/{version}/config.json exists.
  • .zeus/{version}/task.json exists and contains pending tasks unless filtered by --task.
  • .zeus/scripts/zeus-runner.sh exists and is executable.
  • claude CLI is installed and reachable.

Optional filters

  • --task T-###
  • --wave <N>
  • --version vN

Deterministic workflow

1) Build execution plan

Load pending tasks and group by wave.

Show preview summary before running:

  • total task count
  • wave count
  • per-wave task list

Require user confirmation to proceed.

2) Launch runner

bash .zeus/scripts/zeus-runner.sh \
  --task-file .zeus/{version}/task.json \
  --log-dir .zeus/{version}/ai-logs \
  --version {version}

3) Monitor and report

Track runner output and report progress by wave:

  • started
  • completed
  • failed/retry state
  • commit SHA for completed tasks

4) Validate completion

After run, verify:

  • all targeted tasks now have passes: true,
  • commit_sha is filled,
  • milestone status can be promoted to completed when all related tasks pass.

5) Persist post-run updates

Update relevant roadmap milestone status and write summary log.

6) Write execution AI log

Create .zeus/{version}/ai-logs/{ISO-ts}-execute.md.

Per-task execution contract

Each task completion must include:

  1. Quality checks (typecheck/lint/tests when configured)
  2. Atomic commit with format {type}({task_id}): {description}
  3. task.json update (passes, commit_sha, optional ai_log_ref)
  4. Task-level AI log .zeus/{version}/ai-logs/{ISO-ts}-{task_id}.md
  5. Progress append to .zeus/{version}/progress.txt

Brownfield extension:

  • If task includes refactor_of, switch to minimal-intrusion strategy:
    1. Add or update tests around existing behavior first.
    2. Apply smallest safe change in existing modules.
    3. Preserve backward compatibility or provide migration notes.
  • Include refactor_of details in task-level AI log execution summary.

Read the full file on GitHub · 118 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. 1mo ago First seen · 118 lines · 0 tokens per session scan A 89eb1c16d970

Subscribe to this mod's changes

zeus-execute is a skill published in the GitHub repository huifer/zeus (22 stars, last pushed 6mo ago), licensed MIT. It adds 65 tokens to every session and 835 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

zero-to-prod-orchestrator

Master orchestrator to build an application from scratch to a production-ready release, enforcing strict step-by-step progression and continuous documentation / Orkestrator utama untuk membangun aplikasi dari nol hingga rilis siap produksi dengan dokumentasi bertahap.

roedyrustam/vibes-plug · 55 tokens

monorepo-architect

Expert guide for designing and managing scalable monorepos using Turborepo, pnpm workspaces, and shared packages / Panduan ahli untuk merancang dan mengelola monorepo skalabel menggunakan Turborepo dan pnpm workspaces.

roedyrustam/vibes-plug · 57 tokens

n8n-automation-expert

Expert guide for workflow automation (n8n, Zapier, Make), custom nodes, webhook triggers, and AI-powered automation chains / Panduan ahli otomasi workflow (n8n, Zapier, Make), custom nodes, webhook triggers, dan rantai otomasi berbasis AI.

roedyrustam/vibes-plug · 66 tokens

system-brief

Capture one system — the whole assembly of capabilities — as a brief complete enough that each capability line is a one-shot input to /capability-brief and the mission, language, and decisions seed the sbce system doc without a question. Runs the stakeholder interview once, at inception, checks the result against a…

AdamBien/airails · 355 tokens

skill-register-care

Pflege-Skill, der das dreiteilige Skill-Register konsistent hält (code-skill-index-Kataloge, Skill-Index, SKILL-MAP Family-/Routing-Map). Nutze diesen Skill für einen Drift-Check zwischen dem realen Skill-Inventar und dem dokumentierten Register: fehlende oder zu viele Einträge melden, Counts korrigieren, Stand-Datum…

ellmos-ai/skills · 117 tokens

requirement-delivery

A workflow for turning a new software request into a small, working deliverable. It clarifies acceptance criteria, identifies boundaries, breaks work into demonstrable parts, and looks for existing code or tools to reuse.

Wade-DevCode/awesome-coding-skills-cn · 34 tokens