agentmods.dev

wave-orchestrator

wave-orchestrator is a skill for Claude Code from Harshvardhan86/claude-wave-plugin. It costs 84 tokens per session (1,598 once invoked), scanned A, original, MIT.

A coordinator for shipping software features through a defined sequence of planning, design review, implementation, testing, and delivery phases. It can run a full process or a shorter five-phase demonstration.

In plain words
What is it for?
Use it to start a full or demo feature-delivery wave, dispatch work across phases, apply review gates, and manage the workflow through completion.
Why use it?
It keeps the stages, assigned teams, review gates, and handoffs organised while other agents do the implementation work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the claude-wave-plugin plugin — 7 skills, 2 commands shipped together

not rated 8repo 3mo ago A scan 84 tokens original MIT

Good fit Use it to start a full or demo feature-delivery wave, dispatch work across phases, apply review gates, and manage the workflow through completion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/harshvardhan86/claude-wave-plugin/wave-orchestrator
View source ↗ Harshvardhan86/claude-wave-plugin
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.

Any agent
npx skills add Harshvardhan86/claude-wave-plugin --skill wave-orchestrator
Clone the repo
git clone --depth 1 https://github.com/Harshvardhan86/claude-wave-plugin

Made for: Claude Code.

Or install claude-wave-plugin, the plugin that ships this one along with the rest of its 7 skills, 2 commands.

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 wave-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/harshvardhan86/claude-wave-plugin/wave-orchestrator/github.svg)](https://agentmods.dev/skills/harshvardhan86/claude-wave-plugin/wave-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/harshvardhan86/claude-wave-plugin/wave-orchestrator"><img src="https://agentmods.dev/badge/skills/harshvardhan86/claude-wave-plugin/wave-orchestrator/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 wave-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/harshvardhan86/claude-wave-plugin/wave-orchestrator"><img src="https://agentmods.dev/badge/skills/harshvardhan86/claude-wave-plugin/wave-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,598 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 $0.00084 $0.01598
Opus 5 $0.00042 $0.00799
Sonnet 5 $0.00017 $0.00320
Haiku 4.5 $0.00008 $0.00160

Measured 9d ago against content hash 310813c59258, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wave-orchestrator 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 9d 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/wave-orchestrator/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wave Orchestrator

You are the single coordinator of a wave. You dispatch and gate; you do not implement. The framework in framework/SKILL.md is the canonical specification — your job is to execute it faithfully or, in --demo mode, to run the trimmed entry-level subset.

Modes

The /wave-start command tells you which mode to run:

Default mode — full v2 framework

When invoked without --demo, you execute the canonical pipeline specified in framework/SKILL.md: 17 base phases plus the conditional [DR] Design Review at Phase 1.5 (mandatory whenever the wave ships UI — web, mobile, Storybook, CLI-TUI; skipped silently otherwise) and the optional [CR] Code Review at Phase 3.5 (opt-in via the orchestrator's cr_enabled flag). Maximum surface per wave: 19 phases.

Before dispatching anything:

  1. Read framework/SKILL.md for the phase table and invariants.
  2. Read framework/references/02-standing-teams.md for orchestrator/permission/dashboard/checkpoint/bug-ops/cleanup team definitions.
  3. Read framework/references/03-wave-pipeline.md for full per-phase team rosters and model assignments.
  4. Read framework/references/10-model-routing.md to set Opus/Sonnet/Haiku correctly on each Agent dispatch.
  5. Read framework/references/07-invariant-rules.md. The 10 invariants are non-negotiable.

Then dispatch each phase per the framework. Use isolation: "worktree" on writing dispatches per framework/references/08-worktree-strategy.md. Use run_in_background for the Dashboard team and long Playwright runs. Hook enforcement of invariants 6 and 7 is documented in framework/references/11-hooks-and-automation.md — verify settings.json has them wired or surface the gap.

Do not summarise the framework here. Read it. The framework is the spec; this skill is the router.

--demo mode — trimmed 5-phase entry subset

When invoked with --demo, you skip the full pipeline and run a tractable subset designed for live audiences and small UI features. The phases are:

Read the full file on GitHub · 100 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. 9d ago First seen · 100 lines · 84 tokens per session scan A 310813c59258

Subscribe to this mod's changes

wave-orchestrator is a skill published in the GitHub repository Harshvardhan86/claude-wave-plugin (8 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 1,598 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 2026-08-31.

Claude CodeFrontendOrchestrationagent-frameworksclaude-code-plugindesign-review
Related

Other skills, from other repositories

visual-verify

Use when about to declare done on any output with a visual surface -- an HTML page, a rendered UI, a diagram, a slide, a screenshot-able view -- to confirm by looking at the rendered result instead of asserting it. Also use when asked to screenshot or visually check a page or a local file.

metraton/gaia · 66 tokens

gaia-audit

Use when the user asks to audit, check, or review a Gaia component (an agent or a skill) against its standard and its live implementation -- "audita este skill", "chequea este agente", "¿está bien esta skill con la implementación?", "¿cómo mejoro este agente?".

metraton/gaia · 67 tokens

agent-creation

Use when creating a new specialist agent for Gaia, or reviewing whether an existing agent follows the correct structure, tone, and component inventory.

metraton/gaia · 30 tokens

vibe-code

Vibe-code with a loaded design system — browser-automated visual testing.

qGolem/orc · 15 tokens

redesign-existing-projects

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

biggora/dev-team · 45 tokens

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…

biggora/dev-team · 90 tokens