Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsClaude Wave Plugin: Evidence-First Engineering Waves
Run Claude Code like an engineering org: a dedicated sub-agent per phase, strict TDD, visual verification gates and hook-enforced phase order.
Free
Claude Wave Plugin: Evidence-First Engineering Waves
Example session with this skill installed
/wave-start --demo "make the save button show a loading spinner"
- Read your context and instructions
- Compiled the claude wave plugin
Summary
The orchestrator runs the 5-phase demo wave (AC, DR, RED, GREEN, TEET). Each phase is a separate sub-agent with lean context, and every hand-off is gated on evidence files under .wave/.
What happens, phase by phase
| # | Phase | Sub-agent | Evidence produced |
|---|---|---|---|
| 1 | Acceptance Criteria | ac-writer | .wave/ac.md: brutal, falsifiable ACs (spinner visible while saving, button disabled, spinner gone on success/error) |
| 2 | Design Review | design-reviewer | .wave/dr.md: audit of your design system's installed dist files, per-route mockup, computed-style visual ACs. Any design-system gap becomes an OPEN item that pauses the wave |
| 3 | RED | red-tests | Failing tests written against the ACs, with the failure output printed as proof |
| 4 | GREEN | green-impl | Minimum implementation, live stack started, full test suite run, Playwright screenshot taken |
| 5 | Visual approval | orchestrator | The wave stops, shows you the screenshot and asks you to confirm before going on |
| 6 | TEET | teet-verify | Cross-system computed-style and boundingBox assertions, plus the final verdict |
Example of a visual AC it enforces
// Not toBeVisible(): that passes for a 0x0 element
const box = await spinner.boundingBox();
expect(box.width).toBeGreaterThan(0);
expect(await spinner.evaluate(e => getComputedStyle(e).animationName)).not.toBe('none');
The rule to remember
If the agent says "done" without showing you a screenshot, refuse the hand-off. That is exactly the failure mode the plugin exists to prevent.
Next steps
- After two or three successful
--demowaves, drop the flag:/wave-start "implement the new payment flow"runs the full 17-phase pipeline with [DR] and optional [CR]. - If context fills mid-wave, run
/wave-checkpointand resume in a fresh session.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop vibe-coding. claude-wave-plugin turns Claude Code into an orchestration layer instead of an autocomplete. Every phase of shipping a feature gets its own dedicated sub-agent with lean context, and the orchestrator only accepts a hand-off when it sees real evidence: live-stack screenshots, computed-style assertions and true end-to-end runs. "Build clean" or "tsc passes" is never enough.
The defaults of vibe-coding optimise for time-to-first-demo. This plugin optimises for time-to-shippable.
The problem it solves
One-shot prompting produces fake-done features in production codebases: tests that pass while the page renders blank, configs that validate but are never read at runtime, a data-theme="dark" attribute that is set while the screenshot stays light. Wave execution makes those failures impossible to hand off.
What you get
- Full Wave Execution Framework v2: 17 base phases plus two conditional gates, [DR] Design Review (mandatory for UI waves) and [CR] Code Review (opt-in). Brutal ACs, Silent Error Analysis, Dependency Audit, Brutalised E2E, version bump, commit, cleanup, checkpoint.
- Model routing: Opus advises (plan, critique, decide), Sonnet executes (code, tests, scans), Haiku handles mechanical steps.
- Hook enforcement (v0.2.x): phase order, valid phase/role/model, hand-off artifacts and markers, UI screenshot approval and bug-fix strategy approval are gated by executable hooks, not by trust.
- Checkpoint resume:
/wave-checkpoint(and an automatic PreCompact checkpoint) writes resume state to.wave/checkpoints/, so auto-compact or a dead battery never kills a run. - Token ledger and scorecard: per-agent model and token accounting, budgets and rework tracking.
Skills included
| Skill | Phase | Owns |
|---|---|---|
| wave-orchestrator | Router | Full/demo/solo dispatch and hand-off gates |
| ac-writer | 1. Acceptance Criteria | Brutal, falsifiable ACs |
| design-reviewer | 1.5 Design Review | Component API audit against installed dist files, per-route mockup, visual ACs |
| red-tests | RED | Failing tests first, proven to fail |
| green-impl | GREEN | Minimum code, then live stack + full tests + screenshot |
| teet-verify | TEET | True end-to-end with computed-style and boundingBox assertions |
| wave-execution-framework-v2 | Canonical spec | The 17-phase pipeline, 10 invariants and 12 reference docs |
Commands
/wave-start "<feature>": full v2 pipeline/wave-start --demo "<feature>": trimmed 5-phase entry subset (AC, DR, RED, GREEN, TEET). Start here./wave-start --solo "<feature>": direct task with explicit models, commit guard, checkpoint and ledger/wave-checkpoint: save wave state to disk
The 5 hard-won rules
- Verify before scan: never scan un-verified GREEN.
- Visual effect over DOM presence:
toBeVisible()is true for a 0x0 element, so assert computed styles and bounding boxes. - Visual vocabulary grounding: never invent a colour or token the app does not already render.
- Never implement without wiring: trace config to runner to handler end-to-end.
- Permissions once, upfront.
Best for
Production codebases where bugs cost money and "the agent said it's done" is not acceptable evidence. For quick prototypes or one-line fixes, plain prompting is faster.
Open source (MIT): https://github.com/Harshvardhan86/claude-wave-plugin
What's included (7 skills in this plugin)
wave-execution-framework-v2
Use when executing multi-wave engineering work needing strict TDD, bug-capture/fix split, quality gates, and orchestrated teams with per-agent Opus-advisor / Sonnet-executor model routing.
ac-writer
Use as the first phase of a wave. Drafts brutal, testable acceptance criteria for a feature. Each AC must be falsifiable by a real-world test. Output written to .wave/ac.md.
design-reviewer
Use after AC and before RED for any wave that ships UI. Performs component API audit against installed dist files, produces per-route mockup, defines visual ACs, flags design-system gaps. Output written to .wave/dr.md.
green-impl
Use after RED is verified failing. Writes the minimum code to make RED tests pass, then verifies on a live stack with Playwright screenshots before any hand-off. Implements the verify-before-scan rule.
red-tests
Use after DR and before any production code is written. Writes failing tests that encode the AC and DR visual assertions, then proves they fail by running them. RED phase of TDD — strict, no exceptions.
teet-verify
Use only after the user has approved the GREEN screenshot. Performs True End-to-End Testing across backend, frontend, DB, and external services with computed-style and boundingBox assertions, producing the final wave evidence pack.
wave-orchestrator
Use when shipping a feature end-to-end. Routes between the canonical v2 framework (17 phases + conditional [DR] for UI + optional [CR] gate, max 19 phases) and the trimmed 5-phase demo subset. Invoked by /wave-start and /wave-start --demo. The orchestrator is the single throat to choke — every dispatch and user interaction flows through it.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 2 days ago
- Free to download with an account
Requires
Git
Node.js