cmd-diet
by Vedant Andhale · ★ 4 · updated yesterday
Adds quiet flags to noisy shell commands before they run (git status, pytest, cargo, npm install, mvn, curl, wget, docker pull), so Claude reads short output from the start; errors, failures and warnings stay in full.
Install
/plugin marketplace add VedantAndhale/claude-pro-kit/plugin install cmd-diet@claude-pro-kitThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
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
tool.call- API calls
$.ui.status- Can see
every tool call- Reach
- level 0 of 3 draws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/VedantAndhale/claude-pro-kit
- Path in repo
plugins/cmd-diet- Source commit
458068athe exact code the scan read- Author
- Vedant Andhale @VedantAndhale
- License
- MIT
- First published
- Last pushed
- First listed here
- On X
- Mentioned in 1 post on X
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.
Posts about this repo
@davekiss @jarrodwatts @ihamzafer Great i have few of my scripts doing similar with twist I will soon be getting a kit for my self as mods from my scripts. Mods has really enabled claude to make more coustom experience with llms after skills. https://github.com/VedantAndhale/claude-pro-kit
More from VedantAndhale/claude-pro-kit
agent-diet
VedantAndhale/claude-pro-kit
Runs search-only subagents (Explore by default) on Haiku instead of your main model; a model Claude asks for still wins, and /agent-diet picks the types and the model.
answer-pane
VedantAndhale/claude-pro-kit
Explain, plan and ELI5 pages drawn natively in a side pane: diagrams in place, plan decisions as buttons, Respond fills the prompt box. No model calls.
budget-guard
VedantAndhale/claude-pro-kit
Holds a prompt back once your 5-hour or weekly usage is at or over a limit you set (90% by default); sending it again goes through. No tokens spent.
cache-clock
VedantAndhale/claude-pro-kit
Shows how long the prompt cache stays warm, and when it expires, exactly how many tokens your next message will re-send uncached. No tokens spent.
collision-guard
VedantAndhale/claude-pro-kit
Asks before Claude edits a file another chat on this machine changed in the last 30 minutes. Each chat keeps its own small ledger; no model calls, no network.
compact-keeper
VedantAndhale/claude-pro-kit
After a compaction, adds one message with exact facts from before it: your latest prompt in full, up to 4 earlier ones, the files edited, the todo list and the last failed shell command. At most 4,000 characters. No model calls.
context-xray
VedantAndhale/claude-pro-kit
A pane with the exact breakdown of what fills Claude's context: system prompt, tools, memory files, skills, messages, and which tools load on every request.
gh-account
VedantAndhale/claude-pro-kit
Runs each git push, pull, fetch, clone and gh command as the logged-in GitHub account that owns or belongs to the repository's owner, so Claude stops switching gh accounts and retrying failed pushes.
kit-updates
VedantAndhale/claude-pro-kit
Tells you when a newer version of an installed claude-pro-kit mod is out, and /kit-update installs it along with any new mods you never had. One small download per session, no tokens spent.
loop-guard
VedantAndhale/claude-pro-kit
Holds back a shell command once when the exact same command already failed twice in a row, and tells Claude to change approach; retrying it still goes through.
output-diet
VedantAndhale/claude-pro-kit
Trims long shell output, Grep results and subagent reports before Claude reads them (head, tail and error lines kept); the untrimmed text is saved to a file Claude can open.
peek
VedantAndhale/claude-pro-kit
Typing "status" while background shells or subagents run opens a pane with each task's exact elapsed time, the tail of its output and any percent it printed, instead of sending the prompt to Claude. /peek opens it too. No tokens spent.