compound-engineering-plugin

Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR, and watch CI to green. Use only when the user explicitly asks to build or ship something autonomously all the way to an open PR, or invokes lfg directly — it pushes and opens a PR without stopping. Not for in-the-loop work where the user reviews each step: use ce-plan to plan, ce-work to implement a plan, ce-debug to fix a bug, or ce-commit-push-pr to commit and open a PR for existing changes.

Set up isolated git worktrees — create a new branch for fresh work, or attach a worktree to an existing branch/PR/commit to work on it in isolation. Use when starting isolated work or isolating an existing ref; detects existing isolation first.

Execute a plan or concrete work prompt end-to-end. Use when implementing from a plan document, a spec path, or a clear build request; use ce-debug for open-ended bugs. Standalone use owns the shipping tail; outer orchestrators pass `mode:return-to-caller [implementation_engine:<compact-json>] [implementation_run:<safe-id>] <plan path>` for implementation, recovery, and local verification only.

Build and test iOS apps on simulator with XcodeBuildMCP.

Run browser tests for pages affected by the current branch or PR.

Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged to main, and emit an `lfg`-ready plan. First run sets up sources; supports mode:headless for scheduled runs.

Create or update STRATEGY.md. Use when starting a product, changing direction or roadmap, or when ce-ideate, ce-brainstorm, or ce-plan need upstream product grounding.

Simplify recently changed code for clarity, reuse, quality, and efficiency while preserving behavior. Use for tidy/refactor passes; use ce-debug for bugs.

Check Compound Engineering health and repo-local config.

Analyze Riffrec feedback captures from bundles or standalone recordings. Always load for `riffrec-*.zip`, `session.json` + `events.json` + `recording.webm` + `voice.webm` bundles, `.mp4`/`.mov`/`.webm` videos, `.m4a`/`.mp3`/`.wav` audio, or capture/share requests.

Resolve PR review feedback. Use when addressing review comments, resolving review threads, or fixing code-review feedback.

Publish, read, comment on, or edit markdown in Proof. Use for Proof links, sharing specs/plans/drafts, or publish handoffs from planning workflows; avoid proofread, math, evidence, or proof-of-concept meanings.

Draft launch or promotion copy for a shipped feature.

Generate time-windowed product pulse reports from configured signals.

Give a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a user-supplied approach set. Use for a solo POV, a mid-session second opinion, a named-peer cross-check, any request to consult other models or reconcile their opinions, an `oracle` panel, or a correction-cost-gated proactive cross-check offer. Not for findings review (use ce-doc-review), neutral explainers, or generating options (use ce-ideate or ce-brainstorm).

Start the dev server, inspect the feature in browser, and iterate on polish.

Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.

Run metric-driven optimization loops. Use when improving measurable outcomes such as search relevance, clustering quality, build performance, prompt quality, or scored behavior through experiments.

Generate and evaluate grounded ideas. Use when the user asks for ideas, improvements, surprising options, or AI-generated directions before choosing one to develop; use ce-brainstorm to refine the user's own idea.

Create a session handoff for another agent, or resume, find, and read any user-selected continuity source. Use when work or conversation must continue without access to the current session history.

Create a durable, visual teaching artifact — plus an optional check-in (predict-then-reveal for diffs, corrected exercises) that makes it stick — for something worth learning: a concept, a diff, an idea, or a window of your own recent work. Use when the user wants to be taught, wants a deep explainer, wants to understand a substantial change, or wants a work recap built for retention. Not for ordinary Q&A, brief 'why?' follow-ups, operational diagnosis, status updates, or a concise trade-off answer that belongs inline in chat. For learning, not repo docs or verdicts.

Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests and commits, judges experience against product personas, and writes a durable dogfood report. Manual invocation only.

Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.

Diagnosis loop for bugs and failing behavior. Use for errors, stack traces, regressions, failed tests, issue-tracker bugs, stuck investigations after failed fixes, or asks to debug/fix a bug.

Document a recently solved problem as a durable repo learning, or capture project vocabulary in CONCEPTS.md. Use when capturing a learning after work.