ClaudeCodeMod

All shelves / Mods / Review

prompt-enhancer

By vumichien

prompt-enhancer is a Claude Code review mod by vumichien.

Draws an Enhance button above the prompt: Haiku rewrites your draft to name fitting skills, what to ask first, and what done looks like. It never sends it.

Draws

Install

The marketplace name is chien-mods.

In your shell
claude plugin marketplace add vumichien/claude-code-mods-kit
claude plugin install prompt-enhancer@chien-mods
Open the repo

It runs inside the Claude Code process. The side panel is only what the author's README names. Read the repo before you install, or run claude plugin validate on the plugin folder.

Version
0.1.0
License
MIT
Repo stars
4
Last change
2026-10-10

What it can reach

  • Draws in the session

Start a new session after installing, then turn it on with /prompt-enhancer on; it starts off. Tested on Claude Code 2.1.296 on Windows 11; mods are an early-access feature, so the API can change between versions. Nothing happens until you press Enhance, which is e after Ctrl+X, with Tab giving the band the keyboard. It then sends Haiku one request holding your draft, the name and the first 100 characters of the description of each skill and command your session has, built-in commands left out, and the first 40 lines of the project's CLAUDE.md. It sends nothing when the draft is empty, is longer than 4,000 characters, or holds a value shaped like a key. After 20 seconds it gives up and the draft stays. It has no options. To try it for one session without installing, git clone the repository and start claude with --plugin-dir pointing at the mod's folder.

The marketplace, chien-mods, also holds secret-guard, plan-meter, done-gate, context-meter, idea-shelf, session-monitor, and assumption-check, each installed on its own. Improving a prompt before you send it is why this page files it under review. prompt-polish, by VedantAndhale, rewrites the draft in the prompt box when you press Improve, with one model call, and does not send the rewrite. prompt-polish-jheroorehj rewrites your prompt with the prompting guide for the session's model before it is sent, and shows the polish beside the original to apply, retry, or keep. This one asks Haiku to name the skills that fit your session, list what Claude should ask you first, and say what done looks like. If you edited the draft while it worked, your edit wins and the rewrite is dropped. The README counts its model call as one of the calls Claude Code makes, costing about $0.001 in the one press it measured, and says that on a Claude subscription such calls count against your usage.

Demo

The prompt-enhancer paragraph of the author's claude-code-mods-kit README: nothing happens until you press Enhance, then Haiku gets one request with your draft, the skills and commands of the session, and the first 40 lines of CLAUDE.md; it sends nothing for an empty draft, one over 4,000 characters, or one holding a key-shaped value; a rewrite replaces the draft in a few seconds, your own edit wins, it gives up after 20 seconds and never submits; the author's measured press took 6,615 input and 661 output tokens, about $0.001.
Screenshot of the author's GitHub page.

What it hooks into

  • session.startWhen a session starts
  • command.runWhen you run its slash command/prompt-enhancer
  • ui.renderDraws into the sessionAbovePrompt

Read from the on() calls in its hook modules. Open its source under Files to check what each one does.

Slash commands 1

  • /prompt-enhancerSwitch the Enhance band on or off, or show what the last rewrite cost

Files

The author's source, 3 files. They load when you open them.

Facts

Author
vumichien
Category
Review
Marketplace
chien-mods
Repo
vumichien/claude-code-mods-kit
Folder
plugins/prompt-enhancer
Version
0.1.0
License
MIT
Repo stars
4
Last change
2026-10-10
Language
TypeScript
Files
7

Other mods in Review

assumption-checkvumichienLists the choices Claude made that you did not state after a turn that edited files or ran commands; mark each right or wrong and send the corrections.replay-theaterAnthropicAdds /replay. Steps through the files Claude edited last turn, one diff at a time.review-watchhamzaferDraws one line above the prompt per running code review, with the model, the target, the elapsed time, and Codex's latest output. A toast lists the findings.md-previewhamzaferWhen Claude edits Markdown, draws the before and after beside the session, rendered the way GitHub does.files-touchedSingh-APDraws one line above the prompt for files Claude changed this session, with lines added and removed. /touched pane lists them, and a press inserts @path.change-ledgerarasovicDraws a pane of every file this session touched, with lines added and removed and which agent edited it, beside the git working tree.turn-timelinearasovicDraws the current turn as a timeline: one lane for the main loop, one per subagent, the split between model, tools, and idle, and the three slowest steps.show-mearasovicDraws each mermaid diagram in an answer as a picture in a pane once the turn ends. /show-me asks for an answer in diagrams.image-peekarasovicDraws thumbnails of images you paste, above the prompt while you write, and larger pictures under the message once it is sent.plannotatorbacknotpropOpens Claude's plan in a review UI where you mark it up, sends your annotations back, and shows what changed when the plan comes back.filetreedata-goblinDraws an IDE-style file tree beside the transcript that lights up what Claude reads, writes, and commits, and follows it through the folders.skinshellosverreRedraws tool rows, code, diffs, tables, math, and Mermaid charts as cards, with a usage band, a calm mode, and fifteen themes; /skin swaps them live.
All 145 in Review