Claude Code mod

prompt-strip

Strips, rewrites and reorders what Claude Code loads into every session: system prompt sections, first-message context, per-turn reminders, tool descriptions, skill bodies, the subagent listing and command descriptions, and adds sections of your own. Edited in its dashboard at http://127.0.0.1:5199, opened with /prompt-strip; needs node on the PATH.

Context & usage modsValidates on Claude Code 2.1.319 Source

Install

From source
git clone https://github.com/MahadSalim/claude-mods.git
claude --plugin-dir ./claude-mods/prompt-strip

The repo has no marketplace file, so load the plugin folder directly with --plugin-dir.

What it can access

Reach
L3Network: network, runs processes, writes files, reads files, reads env vars, reads the system prompt, draws
Sees
the system prompt, every skill
Hooks
session.startturn.startturn.completecommand.runprompt.composeprompt.contextprompt.attachmenttool.describeskill.promptagent.offercommand.describe

From a static scan of the mod's code by awesome-claude-code-mods. It shows what the code asks for, not a security review.

How Claude Code mods work

  • A mod is a plugin with a JavaScript or TypeScript module that runs inside Claude Code (version 2.1.287 or later). It can draw panes beside the transcript, a band above the prompt, buttons and toasts, restyle the spinner and tool rows, and watch or rewrite tool calls and prompts.
  • It installs like any plugin: add its marketplace with /plugin marketplace add owner/repo, then /plugin install name@marketplace.
  • Check what a mod can reach before installing: it runs with your permissions. Reach goes from drawing only, to reading files, to writing files or running processes, to the network. Run claude plugin validate on a clone to list its hooks and calls without running it.
  • Turn one off from the Installed tab in /plugin, or start Claude Code with --safe-mode to skip every customization for a session.
Claude Code docs

Details

Repository
MahadSalim/claude-mods
Folder
prompt-strip
Type
Context & usage mods
Last updated
4 November 2026
Listed in
awesome-claude-code-mods

FAQ

What is prompt-strip?

Strips, rewrites and reorders what Claude Code loads into every session: system prompt sections, first-message context, per-turn reminders, tool descriptions, skill bodies, the subagent listing and command descriptions, and adds sections of your own. Edited in its dashboard at http://127.0.0.1:5199, opened with /prompt-strip; needs node on the PATH. It is a mod for Claude Code, from MahadSalim/claude-mods on GitHub.

What can the prompt-strip mod access?

Its widest reach is "network" (network, runs processes, writes files, reads files, reads env vars, reads the system prompt, draws). It sees the system prompt, every skill. Like any mod, it runs with your permissions.

How do I install prompt-strip?

Clone MahadSalim/claude-mods and start Claude Code with --plugin-dir pointing at the mod's folder (prompt-strip).

More context & usage mods

prompt-shaper

anhtuan23004/claude-mod

Rewrites short, casual prompts with a fast model into Context / Objective / Steps / Output / Constraints, then lets you send the shaped or the original version

Context & usage mods/plugin install

prompter

niijoey/prompter-mod

Talk through what you want, get the right terms and a clean brief for Claude, with this repo's context filled in.

Context & usage mods/plugin install

prompt-quest

tomikng/prompt-quest

An RPG layer for Claude Code: earn XP from sharp prompts and lean token use, spend skill points on perks, and learn AI lore.

Context & usage mods/plugin install

promptsign

PromptSign/promptsign-plugin

Verifies signatures on the instruction files Claude Code loads, meaning CLAUDE.md, skills, and agent definitions, before they reach model context. It re-checks a skill bundle before the Skill tool runs it. Sigstore keyless, offline verification against a pinned trust root, no telemetry.

Context & usage mods/plugin install

prompt-ladder

JunSeo99/prompt-ladder

Claude does what you ask, so ask well. Press ctrl+q on a rough draft and prompt-ladder writes a well-built prompt from your session's own context, at the cost you pick: quick, balanced or deep.

Context & usage mods/plugin install

pruebas-e2e

fran343/claude-mods

Con /playwright, lee el manifest y el contexto del desarrollo y genera y ejecuta pruebas Playwright en la sandbox de Salesforce.

Context & usage mods/plugin install

Browse the most popular Claude Code mods, all context & usage mods, or the skills and MCP server directories.