ce-polish

A guided workflow for improving the user experience of an already working feature through feedback in a live browser. It focuses on requested visual and interaction changes.

In plain words
What is it for?
Use it to inspect a running page, apply focused UX changes, check the result with live reload, and save the requested improvements in local commits.
Why use it?
It gives developers a focused way to turn direct user observations into saved interface fixes. The work ends when the requested polish is complete or a reported blocker prevents it.

Skill for Claude CodeCodex

Part of the compound-engineering plugin — 29 skills, 1 command, 25 agents shipped together

Install

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.

agentmods
npx agentmods add skills/everyinc/compound-engineering-plugin/ce-polish
Any agent
npx skills add EveryInc/compound-engineering-plugin --skill ce-polish
Clone the repo
git clone --depth 1 https://github.com/EveryInc/compound-engineering-plugin

Made for: Claude Code, Codex.

Or install compound-engineering, the plugin that ships this one along with the rest of its 29 skills, 1 command, 25 agents.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 390 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00390
Opus 5 $0.00014 $0.00195
Sonnet 5 $0.00006 $0.00078
Haiku 4.5 $0.00003 $0.00039

Measured 3d ago against content hash e3f5f3cc660a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/detect-project-type.sh, scripts/read-launch-json.sh, scripts/resolve-package-manager.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/ce-polish/SKILL.md · 22 lines

What it actually says

Polish

Put a working feature in front of the user and turn their live observations into focused UX fixes on the running page.

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 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, but it never pushes or opens a PR.

Run

  1. Get the live page ready. Read references/run.md before resolving the requested ref or starting anything. It owns existing-worktree safety, dev-server discovery, the bundled-script calls, reachability, and the browser handoff.
  2. 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.
  3. 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.
  4. Close locally. When the user says they are done, invoke ce-commit for the polish changes, then report the commit(s), the still-running server URL, and any residual blocker.
Changes

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.

  1. 3d ago First seen · 22 lines · 28 tokens per session scan A e3f5f3cc660a

Subscribe to this mod's changes

ce-polish is a skill published in the GitHub repository EveryInc/compound-engineering-plugin (24,760 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 390 once invoked, about $0.0001 per session on Opus 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.