Compound Engineering
AI skills that make each unit of engineering work easier than the last.
Philosophy
Each unit of engineering work should make subsequent units easier -- not harder.
Traditional development accumulates technical debt. Every feature adds complexity. Every bug fix leaves behind a little more local knowledge that someone has to rediscover later. The codebase gets larger, the context gets harder to hold, and the next change becomes slower.
Compound engineering inverts this. 80% is in planning and review, 20% is in execution:
- Plan thoroughly before writing code with
/ce-brainstormand/ce-planusing one readiness-based plan artifact - Review to catch issues and calibrate judgment with
/ce-code-reviewand/ce-doc-review - Codify knowledge so it is reusable with
/ce-compound - Keep quality high so future changes are easy
The point is not ceremony. The point is leverage. A good brainstorm makes the plan sharper. A good plan makes execution smaller. A good review catches the pattern, not just the bug. A good compound note means the next agent does not have to learn the same lesson from scratch.
Learn more
- Skill documentation catalog
- Compound engineering: how Every codes with agents
- The story behind compounding engineering
Workflow
The core loop is six steps: brainstorm the requirements, plan the implementation, work through the plan, simplify what you wrote, review the result, then compound the learning -- and repeat with better context.
| Skill | Purpose |
|---|---|
/ce-brainstorm | Interactive Q&A to think through a feature or problem and write a requirements-only unified plan before planning |
/ce-plan | Enrich feature ideas or requirements-only plans into implementation-ready plans |
/ce-work | Execute implementation-ready plans with worktrees and task tracking |
/ce-simplify-code | Refine the freshly written code for clarity and reuse before review |
/ce-code-review | Multi-agent review against the plan before merging |
/ce-compound | Capture the learning into docs/solutions/ so the next loop starts smarter |
Each cycle compounds: /ce-compound writes learnings that the next /ce-brainstorm and /ce-plan read as grounding -- brainstorms sharpen plans, plans inform future plans, reviews catch more issues, patterns get documented. That return arrow is the whole point.
Additional skills
These sit around the loop or get reached for on demand -- not every cycle needs them.
| Skill | When to reach for it |
|---|---|
/ce-ideate | Before the loop, when you don't yet know what to build -- generates and critically ranks grounded ideas, then routes the strongest one into /ce-brainstorm |
/ce-strategy | Upstream anchor -- creates and maintains STRATEGY.md, read as grounding by ideate, brainstorm, and plan so strategy choices flow into every feature |
/ce-product-pulse | Outer loop -- a time-windowed report on what users actually experienced (usage, performance, errors), saved to docs/pulse-reports/; its follow-ups feed back into ideation and brainstorming |
/ce-debug | Instead of brainstorm -> plan -> work when the input is a bug rather than a feature -- reproduce, trace root cause, fix, then polish/review before PR handoff when warranted |
/ce-pov | On demand, before you commit -- a decisive, project-grounded verdict on whether to adopt, switch to, or revisit an external technology, library, pattern, or platform; works cold or mid-session, and proposes the next step (/ce-plan, /ce-brainstorm, or a spike) from the verdict |
/ce-explain | On demand, to keep learning -- turns a concept, a diff, an idea, or "what did I do this week?" into a dense, visual explainer written for you personally, with an optional check-in (predict-then-reveal for diffs, corrected exercises) that makes it stick |
For the full catalog and how each skill chains together, see docs/skills. The complete inventory is below.
Quick Example
Finding a direction -- when you don't have a specific idea yet, ideate first, then carry the strongest survivor into the loop:
/ce-ideate new drawing tools
/ce-ideate surprise me
/ce-ideate github issues # ground ideas in your open issues instead of a prompt/ce-ideate does the homework first (codebase, past learnings, prior art on the web, optionally your issue tracker), then hands you a ranked set of grounded candidates to take into /ce-brainstorm.
Standard feature loop -- turn a rough idea into shipped, reviewed code:
/ce-brainstorm make background job retries safer
/ce-plan
/ce-work
/ce-simplify-code
/ce-code-review
/ce-compoundSimplifying code -- use it after fresh implementation work, or point it at code that keeps slowing changes down:
/ce-simplify-code
/ce-simplify-code simplify the code in my most-churned fileThe first pass tightens recent branch changes before review. The targeted pass is useful when one file keeps absorbing unrelated fixes, follow-ups, or merge conflicts.
Debugging a bug -- when you start from broken behavior instead of a feature:
/ce-debug the checkout webhook sometimes creates duplicate invoices
/ce-code-review
/ce-compoundAutonomous -- hand off a feature and let the agent run the whole pipeline:
/ce-brainstorm describe the feature
/lfg/lfg runs the loop hands-off: it plans, works through the plan, simplifies, runs code review and applies the fixes, runs browser tests, commits, pushes, opens a PR, then watches CI and repairs failures until it's green. Start it after /ce-brainstorm so it plans against real requirements rather than a one-line prompt. It's the autopilot version of the standard loop -- neat when you want to step away and come back to an open, green PR.
Getting Started
After installing, run /ce-setup in any project. It checks repo-local config, reports optional tool capabilities, and helps keep machine-local CE settings safely gitignored.
The compound-engineering plugin currently ships 29 skills and 0 standalone agents. Specialist review, research, and workflow behavior lives inside the owning skills as skill-local prompt assets.
Full Skill Inventory
| Skill | Purpose |
|---|---|
/ce-strategy | Create or maintain STRATEGY.md |
/ce-ideate | Generate and critically evaluate grounded ideas |
/ce-pov | Form a decisive, project-grounded verdict on an external input |
/ce-explain | Explain a concept, diff, idea, or window of your own work as a personal learning artifact |
/ce-brainstorm | Explore requirements and write a right-sized requirements doc |
/ce-plan | Create structured implementation plans |
/ce-work | Execute implementation plans systematically |
/ce-code-review | Review code with skill-local reviewer personas |
/ce-doc-review | Review requirements and plan documents |
/ce-debug | Reproduce failures, trace root cause, fix bugs, and prepare non-trivial fixes for PR |
/ce-compound | Document solved problems to compound team knowledge |
/ce-compound-refresh | Refresh stale or drifting learnings |
/ce-optimize | Run iterative optimization loops |
/ce-product-pulse | Generate time-windowed product pulse reports |
/ce-riffrec-feedback-analysis | Convert Riffrec recordings or notes into structured feedback |
/ce-sweep | Sweep feedback sources, track item lifecycles, and emit an /lfg-ready plan |
/ce-resolve-pr-feedback | Resolve PR review feedback |
/ce-commit | Create a git commit with a clear message |
/ce-commit-push-pr | Commit, push, and open a PR with related work references preserved |
/ce-worktree | Ensure work happens in an isolated git worktree |
/ce-promote | Draft user-facing announcement copy |
/ce-test-browser | Run browser tests on PR-affected pages |
/ce-test-xcode | Build and test iOS apps on simulator |
/ce-setup | Diagnose optional tool capabilities and project config |
/ce-simplify-code | Simplify recent code changes |
/ce-polish | Start a dev server and iterate on UX polish |
/ce-proof | Create, edit, and share Proof documents |
/ce-dogfood | Hands-off diff-scoped browser QA of the active branch, with autonomous fixes |
/lfg | Full autonomous engineering workflow |
Install
Claude Code
/plugin marketplace add EveryInc/compound-engineering-plugin
/plugin install compound-engineeringAlready have Compound Engineering installed? Compound Engineering moved to a root-native layout. You must refresh the marketplace before updating — see Existing Installs. Running
/plugin updatealone keeps you on the old version.
Cursor
In Cursor Agent chat, install from the plugin marketplace:
/add-plugin compound-engineeringOr search for "compound engineering" in the plugin marketplace.
Codex App
Compound Engineering is not listed in Codex's built-in plugin marketplace yet. Add it as a custom marketplace:
-
In the Codex app, open Plugins from the sidebar.
-
Click Add / Add plugin marketplace.
-
Enter:
Field Value Source EveryInc/compound-engineering-pluginGit ref mainSparse paths leave blank -
Click Add marketplace.
-
Select Compound Engineering, install compound-engineering, then restart Codex.
The Codex app install is self-contained for Compound Engineering. Specialist reviewer and research behavior lives inside the skills as local prompt assets; no separate custom-agent install step is required.
Codex CLI
Register the marketplace, then install the plugin.
-
Register the marketplace with Codex:
codex plugin marketplace add EveryInc/compound-engineering-plugin -
Install the plugin:
codex plugin add compound-engineering@compound-engineering-pluginYou can also launch
codex, run/plugins, find the Compound Engineering marketplace, select the compound-engineering plugin, and choose Install. Restart Codex after install completes.
The native Codex plugin install is self-contained for Compound Engine
…