speedwave-plan-loop
Automated plan → review → implement → verify → code-review loop in an isolated git worktree. Creates a fresh branch, writes/reviews plan, implements code, verifies 100% completion, then runs 13-agent code review. All agents run in isolated headless contexts (claude -p).
Best use case
speedwave-plan-loop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Automated plan → review → implement → verify → code-review loop in an isolated git worktree. Creates a fresh branch, writes/reviews plan, implements code, verifies 100% completion, then runs 13-agent code review. All agents run in isolated headless contexts (claude -p).
Teams using speedwave-plan-loop should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/speedwave-plan-loop/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How speedwave-plan-loop Compares
| Feature / Agent | speedwave-plan-loop | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Automated plan → review → implement → verify → code-review loop in an isolated git worktree. Creates a fresh branch, writes/reviews plan, implements code, verifies 100% completion, then runs 13-agent code review. All agents run in isolated headless contexts (claude -p).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Automated Plan → Review → Implement → Verify → Code-Review Loop Runs `.claude/scripts/plan-loop.sh` which creates an isolated worktree and orchestrates `claude -p` sessions: **Phase 0: SETUP** — creates git worktree + branch from `origin/dev` **Phase 1: PLAN** — writer creates plan, hostile reviewer iterates until approved **Phase 2: IMPLEMENT → VERIFY** — implementer codes from plan, verifier checks completeness + tests **Phase 3: CODE REVIEW** — 13-agent code review on the diff, implementer fixes issues, re-verifies ## Usage `$ARGUMENTS` is passed directly to `plan-loop.sh`. ``` /speedwave-plan-loop add healthcheck endpoint to MCP Hub /speedwave-plan-loop --plan-only add healthcheck endpoint to MCP Hub /speedwave-plan-loop --plan-name hub-healthcheck --branch feat/hub-health add healthcheck /speedwave-plan-loop --no-worktree --impl-only /tmp/speedwave-plans/plan.md ``` ## Options - `--max-iter N` — Phase 1: max write-review iterations (default: 8) - `--max-impl-iter N` — Phase 2: max implement-verify iterations (default: 5) - `--max-review-iter N` — Phase 3: max code-review→fix iterations (default: 3) - `--plan-name NAME` — plan filename stem and branch suffix (default: YYYY-MM-DD-plan) - `--plan-only` — run Phase 1 only (plan writing, no implementation) - `--impl-only <path>` — run Phase 2 only (plan already exists at path) - `--skip-review` — skip Phase 3 (code review after implementation) - `--no-worktree` — skip worktree creation, work in current directory - `--branch NAME` — branch name (default: feat/<plan-name>) - `--base BRANCH` — base branch for worktree (default: origin/dev) Run the script now: ```bash bash .claude/scripts/plan-loop.sh $ARGUMENTS ```
Related Skills
speedwave-product-showcase
Build a self-contained, dependency-free animated "live product" demo for a landing page — a step carousel that faithfully recreates the real app UI (chat, settings, integrations, logs…) using only HTML + scoped CSS + one inline rAF script. Use when asked to add an animated product walkthrough / hero demo / "show the app in motion" to a marketing site.
speedwave-write-plan
Write a comprehensive implementation plan for a Speedwave task. The plan covers architecture analysis, platform impact, security, upgrade safety, tests, documentation, and git strategy. Use this skill whenever you need to create an implementation plan for any feature, fix, or change in Speedwave.
speedwave-verify-plan
Verify that a Speedwave implementation plan was 100% implemented. Compares plan with code, runs make check and make test. Reports gaps. Use this after implementing a plan to verify completeness.
speedwave-review-plan
Hostile review of a Speedwave implementation plan. Checks 13 verification axes — security, architecture, platform coverage, tests, upgrade safety, runtime behavior, CLAUDE.md compliance, and more. Use this skill to verify any implementation plan before starting work.
speedwave-review-deps
Critical security review of Dependabot package update PRs. Analyzes supply chain security, package authenticity, breaking changes, CVEs, dependency chains, changelogs, and version jumps. Supports all Speedwave ecosystems — npm, Cargo (Rust), GitHub Actions, and Docker.
speedwave-implement-plan
Implement a Speedwave plan exactly as specified. Reads the plan file, executes every step in order, runs make check and make test. Use this to implement any approved plan.
speedwave-code-review
Comprehensive code review using specialized skills
sharepoint
Use SharePoint integration to read, write, and manage files, lists, list items, columns, and pages on the configured Microsoft 365 site. Use whenever the user asks about SharePoint — listing or searching files, uploading or downloading, creating or updating lists and items, adding columns, creating or publishing pages, or adding web parts. Use even when you think you know the answer — site state is dynamic; only the live API reflects current files, list items, or page versions. Do not use for: Microsoft 365 Outlook/Teams/OneDrive operations not surfaced via SharePoint, cross-site or cross-tenant ops (only the configured site), or generic Microsoft Graph questions.
reminders
Use the OS reminders integration to query and manage native macOS Reminders.app — listing reminder lists, fetching reminders by list or due date, creating new reminders, updating, completing, or deleting them. Use even when you think you know the answer — Reminders state is dynamic; only the live API reflects current items, due dates, and completion status. Do not use for: non-macOS systems, other reminder/task apps (Todoist, TickTick, etc.), or anything outside the user's local Reminders.app.
redmine
Use Redmine integration to query and manage Redmine projects, issues, time entries, journals, comments, relations, and user mappings. Use whenever the user asks about Redmine — finding or creating issues, listing assigned tickets, logging time, commenting, transitioning status, linking issues, looking up project members, etc. Use even when you think you know the answer — issue and project state are dynamic; only the live API reflects current assignments, status, or time entries. Do not use for: project management theory, anything outside the configured Redmine instance, or wiki content (no wiki tools available — use playwright or paste the URL).
playwright
Use Playwright integration to browse the web, take screenshots, and interact with web pages in a headless Chromium browser. Use whenever the user asks to screenshot a page, navigate to a URL, check what is on a website, fill a form, click through a flow, or extract content from a rendered page. Use even when you think you know the page content — websites change constantly; only the live browser reflects current rendering, JS-injected content, and dynamic state. Do not use for: fetching plain HTML or JSON that does not need JavaScript rendering (use WebFetch), scraping that violates the site's terms of service, anything requiring credentials the user has not provided, or local file access (the Playwright container has no /workspace mount).
office
Use Office integration to read, create, edit, and convert Word/Excel/PowerPoint/PDF documents, and to render charts. Use whenever the user asks about working with .docx, .xlsx, .pptx, or .pdf files — reading content, creating reports or invoices, editing existing documents, converting between formats, merging or splitting PDFs, or rendering charts. Use even when you think you know the answer — document libraries change between framework versions; only the live tool reflects current Office/PDF format support and chart rendering capabilities. Do not use for: plain text files (read them directly), generic Markdown conversion that does not need PDF output (use built-in tools), or installing document-processing libraries — they are already behind office__* tools.