By JayPokale
Audit code for over-engineering, compress verbose output, and switch Claude into a terse, efficient mode that prioritizes minimal, correct solutions.
Quick-reference card for RDXmin modes, levels, and commands. One-shot display, not a persistent mode. Use when the user says "rdx help", "how do I use rdx", "what rdx commands", or invokes /rdx-help.
One-shot efficiency audit of a file, diff, or whole repo across BOTH axes at once: over-engineered code (reinvented stdlib, needless abstractions, speculative config) AND bloated prose (verbose comments, padded docstrings, redundant doc sections). Neither a pure code-minimizer nor a pure prose compressor does both in one pass — that's the point. Ranked report, biggest saving first; changes nothing. Use when the user says "rdx audit", "/rdx-audit", "audit this for bloat", "what can I cut", "review this PR for over-engineering and verbosity".
Review a diff or file through the RDXmin lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink. One finding per line, no praise. Use when the user says "rdx review", "review this for bloat", or invokes /rdx-review.
Maximum-efficiency dev mode. Terse, precise prose with zero fluff combined with YAGNI/ladder-first code decisions. One persona: the senior dev who deletes code for fun and bills by the syllable. Supports intensity levels: lite, full (default), ultra. Trigger: /rdx. Deactivate: "stop rdx" / "normal mode". Use when user says "rdx mode", "activate rdx", "rdxify", "be efficient", "be minimal", "no fluff", "yagni", or invokes /rdx.
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
Your AI talks less, builds less, reads less — and says more. Like a senior dev who bills by the syllable.
Half the output bill on 20 measured tasks · compresses what the model writes AND reads · one command
rdx.jaypokale.me — the site version of this README, with fewer words
You asked your AI agent to "add a cache." A bare agent answered with a 150-line cache class — config object, TTL logic, stats counters, the works. RDXmin's answer to the same prompt: 7 lines. Same model, same question, measured, receipts committed in benchmarks/.
Most efficiency tools compress one thing. RDXmin compresses three:
| axis | what | how |
|---|---|---|
| Output: prose | filler, hedging, manufactured structure | zero-fluff ruleset, injected per session |
| Output: code | speculative abstractions, unrequested boilerplate | YAGNI efficiency ladder |
| Input: context | oversized tool output flooding the window | PostToolUse hook — scrub, elide, dedup — plus prevention rules |
Every "be concise" tool has a worst day — the day it makes the model write more than no tool at all. Across 20 measured tasks over two suites, the specialists had that day 6 and 8 times, blowing up to 424% of the baseline. RDXmin had it once, capped at 173% — and that one failure was root-caused, fixed in the ruleset, and re-validated live at 93%, with the whole investigation committed to the repo. Think of it as downside insurance for your token bill: not always the single cheapest answer, always the smallest worst case — from the only tool in this class that publishes its own failures. Why not caveman or ponytail? →
One command. Auto-detects your agents (Claude Code, Cursor, Windsurf, Cline, Kiro, Codex, Gemini, Copilot) and wires each one. --uninstall puts everything back.
npx rdxmin
# or via curl
curl -fsSL https://raw.githubusercontent.com/JayPokale/RDXmin/main/install.sh | bash
# Windows
irm https://raw.githubusercontent.com/JayPokale/RDXmin/main/install.ps1 | iex
Preview first with npx rdxmin --dry-run, scope with --only claude, see everything with npx rdxmin --help. Remove with npx rdxmin --uninstall.
Requirements: Node ≥18 (installer / npx) · Claude Code for live /rdx switching, the statusline badge, and input-side compression — the always-on ruleset still ships to every other agent · bash for the statusline (macOS/Linux; a PowerShell version ships for Windows).
claude plugin marketplace add JayPokale/RDXmin # register the marketplace
claude plugin install rdxmin@rdxmin # enable the plugin
Add to ~/.claude/settings.json:
{
"statusLine": {
"type": "command",
"command": "bash \"/path/to/rdxmin/hooks/rdx-statusline.sh\""
}
}
Nothing here is estimated. Every figure below is recomputed from committed raw data; the 2026-07-07 verification writeup re-derived the old claims from scratch, re-ran the whole suite against the competitors' installed plugins, and retired the one claim that didn't survive.
59+ live model runs across two suites (June 4-arm matrix on Haiku + Sonnet sweep; July re-verification run). Arms differ only in the injected system prompt. Billed output tokens vs the no-tool baseline:
npx claudepluginhub jaypokale/rdxmin --plugin rdxminGovernor: always-on compact professional output, telemetry, context slimming, tool-output filtering, prompt guidance, and drift guardrails for Claude Code Max users.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Verdict-first communication mode. Cuts output tokens while keeping full technical accuracy.
45% cost reduction measured. Cache expiry prevention, SubTask auto-delegation, zero-cost context restoration, real-time cost dashboard. The only Claude Code plugin built from CC source analysis.
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Claude does the work and replies with one word: done. Cuts summaries, preamble, and wrap-up chatter to save output tokens and usage.