prompt-enhancer

by OrchestKit · ★ 296 · updated today

BandsPromptvalidates

0

Review enhanced prompts before sending them

install prompt-enhancer

Install

git clone https://github.com/yonatangross/orchestkit
claude --plugin-dir ./orchestkit/mods/prompt-enhancer

Then run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.

View source on GitHub

What it hooks into

From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.

Events
prompt.submitprompt.changeui.render
API calls
$.model.complete$.prompt.fill$.prompt.read$.prompt.submit$.state.get$.state.set$.ui.resolve$.ui.toast
Draws
AbovePrompt
Can see
every prompt
Reach
level 2 of 3 drives Claudewrites the prompt boxreads the prompt boxreads mod statedraws

Origin

How it got here
Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
Repository
github.com/yonatangross/orchestkit
Path in repo
mods/prompt-enhancer
Source commit
a643dd3 the exact code the scan read
Author
OrchestKit @yonatangross
License
MIT
First published
Last pushed
First listed here

Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.

More from yonatangross/orchestkit

lesson-cards

yonatangross/orchestkit

Displays lesson hint cards when tool calls match known patterns. Additive surface during pilot; the classic --strict guard keeps its 12 block-severity denies.

★ 296ReskinsGuardsCommands

memory-lens

yonatangross/orchestkit

Recalls the few memories related to each prompt: one line for the human, one context entry for the model. Local files only, no network on the hot path.

★ 296GuardsCommandsPrompt

promote-lights

yonatangross/orchestkit

Shows CI status lights above the prompt while a promote PR (base main) is open. One REST page per minute, PR-open only. Cancelled is not-pass.

★ 296BandsStatus lineCommands

secrets-veil

yonatangross/orchestkit

Masks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path.

★ 296Status lineGuards