Compound Engineering is a plugin that organizes software work into brainstorming, planning, implementation, review, and recording lessons for future changes. It is used with AI coding agents including Claude Code, Cursor, and Codex, and the catalogue entries provide parts of its agent, skill, command, and hook workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add EveryInc/compound-engineering-plugin --skill ce-polishgit clone --depth 1 https://github.com/EveryInc/compound-engineering-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/everyinc/compound-engineering-plugin/ce-polish)<a href="https://agentmods.dev/skills/everyinc/compound-engineering-plugin/ce-polish"><img src="https://agentmods.dev/badge/skills/everyinc/compound-engineering-plugin/ce-polish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/everyinc/compound-engineering-plugin/ce-polish"><img src="https://agentmods.dev/badge/skills/everyinc/compound-engineering-plugin/ce-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.00667 |
| Opus 5.5 | $0.00011 | $0.00267 |
| Sonnet 5.5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
ce-polish scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish
Put a working feature in front of the user and turn their live observations into focused UX fixes on the running page. Two ways to collect those observations: traditional, where the user types what could be better; and live, where they talk and draw on the page while a voice interviewer turns speech into units and you act on them at checkpoints.
Done: the user ends the polish loop, every requested fix is reflected in the live feature or reported as blocked, and the in-scope changes are saved in local commit(s). A live session also ends with a residual list of the units that were not applied and the path of its session log. A server or checkout blocker also ends the run when it is reported with the evidence needed to resume.
Boundaries: the user drives what to inspect and change; do not invent an autonomous checklist or expand into general QA. Never work on the repository's default branch. This workflow may edit and locally commit the requested polish, and in live mode the disclosed riffrec setup commit, but it never pushes or opens a PR.
Run
- Ask live or traditional. Ask once, before any server starts. Include this disclosure with the question: live mode needs an OpenAI key in the environment, runs a voice interviewer in the page that hears the user, is told what they click and draw on, and looks at their screen when they point at something or ask it to, streams the session to a local endpoint this skill runs, and, when riffrec is not yet in the app, adds the riffrec dependency and a provider mount as a setup commit on the current branch that stays after the session. Traditional continues with steps 2–5 unchanged. Live: read
references/live-start.md; it owns preconditions, install, the endpoint, and the URL handoff, applies the workspace and server rules ofreferences/run.mditself, then routes toreferences/live-loop.mdfor the session and its close. Steps 2–5 do not run for a live session. - Get the live page ready. Read
references/run.mdbefore resolving the requested ref or starting anything. It owns existing-worktree safety, dev-server discovery, the bundled-script calls, reachability, and the browser handoff. - Wait for observations. Tell the user where the server is running and ask what could be better. Do not start a review pass while they browse.
- Iterate. For each requested change, inspect only as needed, edit the in-scope surface, and let hot reload update the page. When the user asks you to inspect the result, use a browser capability available in the active harness; if none exists, ask them to describe what they see.
- Close locally. When the user says they are done, invoke
ce-commitfor the polish changes, then report the commit(s), the still-running server URL, and any residual blocker.
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 43 B
- references/dev-server-astro.md 1.8 KB
- references/dev-server-detection.md 2.7 KB
- references/dev-server-next.md 1.6 KB
- references/dev-server-nuxt.md 1.7 KB
- references/dev-server-procfile.md 2.3 KB
- references/dev-server-rails.md 2.1 KB
- references/dev-server-remix.md 1.9 KB
- references/dev-server-sveltekit.md 2.0 KB
- references/dev-server-vite.md 2.0 KB
- references/install-riffrec.md 5.1 KB
- references/launch-json-schema.md 4.8 KB
- references/live-loop.md 17 KB
- references/live-remote.md 4.9 KB
- references/live-start.md 14 KB
- references/live-stream-contract.md 32 KB
- references/run.md 5.6 KB
- scripts/detect-project-type.sh 8.8 KB runs code
- scripts/detect-riffrec.sh 8.6 KB runs code
- scripts/live-endpoint.js 119 KB runs code
- scripts/read-launch-json.sh 2.8 KB runs code
- scripts/resolve-package-manager.sh 2.6 KB runs code
- scripts/resolve-port.sh 10.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +1 lines 985888097d7e
- 1mo ago First seen · 22 lines · 28 tokens per session scan A e3f5f3cc660a
ce-polish is a skill published in the GitHub repository EveryInc/compound-engineering-plugin (25,727 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 667 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
senior-data-engineer
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality…
deck-blueprint
A presentation design template for explaining architecture and process pipelines on a cream-colored, blueprint-style background.
prism-component
Implement a reusable, accessible, typed component from a design spec. Use when asked to "create a component", "build a widget", "implement this design", or "reusable UI element".
prism-ui
Implement a complete UI screen or feature from a Form visual spec. Use when asked to "build a page", "implement this screen", "build the frontend for this feature", or "create this UI".
spine-design
Produce a system design doc — components, data flow, decisions made, tradeoffs, failure modes. Not a list of options. An actual design with calls made. Use when asked for "system design for", "architect this", "how should we build", or "design the backend".
prism-dashboard
Build an internal dashboard with data tables, filters, detail views, and CRUD. Use when asked to build an "admin panel", "internal dashboard", "back office", or "data dashboard UI".