Compound Engineering
AI skills that make each unit of engineering work easier than the last.
</div>Compound Engineering is a plugin of 33 skills for AI coding agents. It structures the work around a loop — brainstorm, plan, build, review, then capture what you learned — so the knowledge from each change is written down where the next change can read it.
It runs on 14 agent hosts, including Claude Code, Cursor, and Codex.
Install
Claude Code
/plugin marketplace add EveryInc/compound-engineering-plugin
/plugin install compound-engineering[!IMPORTANT] Already have Compound Engineering installed? Refresh the marketplace before updating — see Upgrading. 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.
Grok Bot
Grok Bot is its own app, but it uses your Cursor account and plugin library. There is no separate Grok Bot login. Install Compound Engineering once on that account and Grok Bot agents can load it.
In Cursor Agent chat:
/add-plugin compound-engineeringOr search for "compound engineering" in the Cursor plugin marketplace. Do not run /add-plugin in the Grok Bot chat, and do not clone this repository onto the Grok Bot computer.
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 the arrow next to Create, then select Add marketplace.
-
Enter:
Field Value Source EveryInc/compound-engineering-pluginGit ref mainSparse paths leave blank -
Click Add marketplace.
-
Search for Compound Engineering, install compound-engineering-plugin, 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 Engineering. Specialist reviewer and research behavior lives inside the skills as local prompt assets; no separate custom-agent install step is required.
For a non-default Codex profile, run every Codex-related step against the same CODEX_HOME. This example installs CE into a work profile:
CODEX_HOME="$HOME/.codex/profiles/work" codex plugin marketplace add EveryInc/compound-engineering-plugin
CODEX_HOME="$HOME/.codex/profiles/work" codex plugin add compound-engineering@compound-engineering-pluginThe marketplace step only makes the plugin available; the plugin install is what activates the native CE skills for that profile.
Another editor or CLI? Kimi Code CLI, Cline, Grok Build CLI, Devin CLI, GitHub Copilot, Factory Droid, Qwen Code, OpenCode, Pi, oh-my-pi (omp), and Antigravity CLI are all supported — see More install options.
Philosophy
Each unit of engineering work should make subsequent units easier -- not harder.
Invocation syntax: this README uses /skill-name examples for slash-skill hosts. In Codex, invoke installed skills with $skill-name (for example, $ce-plan and $lfg). In oh-my-pi (omp), these prompts can model-route to visible skills; use the native deterministic /skill:<name> form for manual-only or hidden skills (for example, /skill:ce-polish). /goal remains a Codex built-in command.
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.
The loop
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 natively or through a qualified cross-model author while retaining host verification, commits, and shipping |
/ce-simplify-code | Refine the freshly written code for clarity and reuse before review |
/ce-code-review | Report-only multi-agent review against the plan before merging; local apply is explicit |
/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.
Run one teaches it. Run two remembers.
<sub>Replayed from a real pair of sessions 18 days apart, with names and paths anonymized and the six-minute run compressed to about 30 seconds. Nothing shown is behavior the skills don't have — see <a href="assets/demo/README.md">assets/demo</a> for the source and the substitutions.</sub>
Artifact folders like
docs/solutions/anddocs/plans/are the defaults. A project whosedocs/is tracked content can relocate every CE artifact folder under one repo-relative root via thedocs_rootsetting -- see configuration.
Try it
After installing, run /ce-setup in any project. It reports optional tool capabilities, creates repo .compound-engineering/config.yaml when missing, refreshes the committed example, and gitignores an existing local override.
The standard 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-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, then commits. When a git remote exists it pushes, opens a PR, and watches CI with a bounded repair loop (it does not merge, and it can finish with leftovers if the repair budget is hit). With no remote it stops at local commits. Start it after /ce-brainstorm so it plans against real requirements rather than a one-line prompt.
Starting from a bug instead of a feature? Use /ce-debug. Not sure what to build yet? Start with /ce-ideate.
Skills at a glance
33 skills, grouped by what they are for. The full catalog, with a page per skill and how each one chains into the others, is in docs/skills.
| Group | Skills | What it covers |
|---|---|---|
| Core loop | ce-brainstorm ce-plan ce-work ce-simplify-code ce-code-review ce-compound | The six steps of every iteration |
| Around the loop | ce-strategy ce-product-pulse ce-sweep ce-compound-refresh | Anchors and feeds that keep the loop grounded |
| On demand | ce-ideate ce-pov ce-debug ce-explain ce-doc-review ce-optimize ce-prototype | Reached for when a specific need arises |
| Git workflow | ce-commit ce-commit-push-pr ce-babysit-pr ce-resolve-pr-feedback ce-worktree | Committing, shipping, and shepherding PRs |
| Autonomous | lfg | The whole pipeline, hands-off |
| Testing & design | ce-test-browser ce-test-xcode ce-polish ce-dogfood | Verifying and polishing what you built |
| Collaboration | ce-proof ce-handoff ce-promote | Sharing work and handing it off |
| Utilities | ce-setup ce-retune ce-riffrec-feedback-analysis | Setup and maintenance |
Learn more
- Skill documentation catalog
- Compound engineering: how Every codes with agents
- The story behind compounding engineering
More Install Options
Claude Code, Cursor, and Codex are at the top. Everything here is equally supported.
Kimi Code CLI
Kimi Code CLI can install Compound Engineering directly from this repository because the repo ships a native .kimi-plugin/plugin.json manifest:
/plugins install https://github.com/EveryInc/compound-engineering-pluginYou can also browse it through Kimi's custom marketplace flow:
/plugins marketplace https://raw.githubusercontent.com/EveryInc/compound-engineering-plugin/main/.kimi-plugin/marketplace.jsonAfter installing or updating, run /reload or start a new Kimi session so the plugin skills are loaded.
Cline
Cline loads CE skills from on-demand SKILL.md directories. Enable Settings -> Features -> Enable Skills in the Cline extension, then link this repository's skills globally or per project:
git clone https://github.com/EveryInc/compound-engineering-plugin
./compound-engineering-plugin/.cline/scripts/install-skills.sh --globalPer-proje
…