What is wave-execution-framework-v2?

A process for carrying out engineering work in ordered waves, with 17 regular phases and optional review phases. It includes test-driven development, or TDD, where tests are written before the implementation, and assigns different agent models to planning, coding, and mechanical tasks.

Use it to coordinate multi-step feature development, bug fixes, quality gates, design reviews, code reviews, and teams of coding agents working in separate Git worktrees.

It separates planning, implementation, testing, reviews, and quality checks so large changes are less likely to skip important steps. For interface work, it adds a design review; a UI is the part of an application that people see and use.

wave-execution-framework-v2 — Skill by Harshvardhan86

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 skills/harshvardhan86/claude-wave-plugin/framework

Any agent

npx skills add Harshvardhan86/claude-wave-plugin --skill framework

Clone the repo

git clone --depth 1 https://github.com/Harshvardhan86/claude-wave-plugin

Made for: Claude Code, Codex.

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

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,685 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.

Model	Per session	Once invoked
Fable 5	$0.00048	$0.02685
Opus 5	$0.00024	$0.01342
Sonnet 5	$0.00010	$0.00537
Haiku 4.5	$0.00005	$0.00268

Measured 3d ago against content hash b3a1093dc4c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wave-execution-framework-v2 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.

framework/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wave Execution Framework v2 — Model-Routed

A multi-wave, multi-team engineering execution framework. Work is decomposed into waves; each wave runs a strict 17-phase pipeline plus two conditional gates: [DR] Design Review at Phase 1.5 (mandatory when the wave ships UI — web, mobile, Storybook, or CLI-TUI) and [CR] Code Review at Phase 3.5 (optional, opt-in). Maximum surface per wave: 19 phases. Enforced by specialized subagent teams (Stream-Aligned, Quality Gate, Platform, Enabling). The orchestrator is the single point of coordination and the single throat to choke.

v2 preserves every phase, invariant, and cardinal rule from v1 and adds three changes that realize the framework against the current (2026) Claude Code / Agent SDK primitives:

Model routing. Every dispatch specifies its model on the Agent tool. Opus = advisory (plan, critique, decide). Sonnet = executor (write code, run tests, scan, fix). Haiku = mechanical (dashboard render, version bump). See references/10-model-routing.md.
Team-as-dispatch-pattern. Nested subagents are not supported in Claude Code, so v2 re-expresses every L2 "team" as either a single Agent dispatch carrying Lead + Executor + Reviewer personas, or a sequence of dispatches the orchestrator coordinates. Fresh-eyes hardening ([ACB], [BSEA], [BTEET]) is enforced by separate dispatches with only the prior output in context. See references/01-architecture.md.
Native platform primitives. isolation: "worktree" on writing dispatches; run_in_background for Dashboard and long Playwright runs; PreCompact / PostToolUse / PreToolUse hooks to enforce invariants; TaskCreate replaces tasks/todo.md; ToolSearch gates the per-phase tool surface. See references/09-platform-deltas.md, references/11-hooks-and-automation.md, references/12-mcp-and-plugins.md.

Read the full file on GitHub · 101 lines

Files

What ships with it

12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 101 lines · 48 tokens per session scan A b3a1093dc4c4

Subscribe to this mod's changes

wave-execution-framework-v2 is a skill published in the GitHub repository Harshvardhan86/claude-wave-plugin (8 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 2,685 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.

Orchestration Planning TDD Testing agent-frameworks claude-code claude-code-plugin design-review

maestro-work

Drive one accepted implementation unit test-first - smallest falsifiable behavior, minimum edits, evidence that names the real falsifier.

ReinaMacCredy/maestro · 28 tokens

debug-flow

Systematic debugging workflow. Reproduce the issue, isolate root cause, write a failing test, fix, verify. Use when diagnosing bugs or unexpected behavior.

DVNghiem/FlowDeck · 34 tokens

tdd-workflow

Enforces Test-Driven Development with Red-Green-Refactor cycle and 80%+ coverage. Activate when writing new features, fixing bugs, or refactoring.

DVNghiem/FlowDeck · 39 tokens

review

Review the supplied artifact for correctness, security, maintainability, and test coverage. Report concrete findings before general suggestions, and distinguish verified defects from risks.

lkimuk/Wuwe · 0 tokens

agent-development-pack

Curated bundle for building, testing, and coordinating AI agent systems. Includes multi-agent orchestration, agent testing, cross-agent handoff, MCP server building, and prompt engineering. Use when developing AI agent workflows or multi-agent systems.

organvm-iv-taxis/a-i--skills · 51 tokens

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code - write the failing test first and watch it fail for the right reason.

andreymudri/claude-teammates · 32 tokens