Measured against caveman & ponytail — and wins

Cut Claude Code's token bill on three axes

A terse dev persona, a tool-output compressor, and context-diet rules — one plugin. Across 20 live tasks it billed 52% of a bare model, with 1 backfire instead of 6 or 8.

GitHub →

or claude plugin marketplace add JayPokale/RDXmin

52%

of a bare model's 20-task bill

1/20

backfires — rivals hit 6 and 8

~46%

shrink on oversized tool output

0

dependencies, network calls, LLM calls

One plugin, three levers

Other token savers only make the model write less. Tool output is the bigger bill — 67.5% of a session — and it re-bills every turn.

How the model writes

Terse persona

Senior-dev voice: fragments over sentences, YAGNI-first code, reuse before new code. Three levels — /rdx lite, full, ultra. Commits and security warnings stay verbose on purpose.

What survives into context

Output compressor

A PostToolUse hook shrinks tool results before the model reads them: ANSI scrub, head + tail elide with error-line salvage, same-session dedup. Never touches Read, Edit, or Write.

What gets read at all

Context diet

Rules that teach the model to fetch the slice, not the file: grep first, sliced reads, filter at the source, never re-read what's already in context.

Live savings statusline

A ⇣9k tok badge showing measured chars elided — real baseline, not an estimate.

Works beyond Claude Code

Generated rulesets for Cursor, Windsurf, Cline, Kiro, and Copilot ship in the same install.

Tested where it matters

The compressor is where a bug corrupts files — it's covered by the test suite, with a hard allowlist.

Easy off-switch

"stop rdx" for the persona, RDX_COMPRESS=0 for the hook, npx rdxmin --uninstall for everything.

400 lines of output. Two matter.

Tool results re-bill on every later turn. The compressor keeps the head, the tail, and the error lines — the rest never reaches the model.

PostToolUse · Bash[RDX]
$ npm test
PASS src/auth/session.test.ts
PASS src/auth/token.test.ts

Deterministic — no LLM calls, no network, no dependencies. Allowlist: Bash, Agent, WebFetch, WebSearch, Grep, Glob, mcp__* — never Read/Edit/Write.

The 20-task bill

Four arms, same 20 live tasks, same model, isolated configs, billed tokens — shown as a share of the bare model. Raw transcripts and the runner ship in the repo.

rdxmin
52%
1 backfire
ponytail
68%
6 backfires
caveman
80%
8 backfires
bare model
100%
baseline

Average task: 69% vs 91% / 98%. Worst single task: 173% vs 227% / 424%. Both rivals are credited in the repo's prior-art table — right above these numbers.

Built in the open

MIT licensed, zero dependencies. Land a PR — or file an issue good enough to fix itself — and you appear here automatically.

JayPokale

Co-engineered with Claude, Codex & Antigravity · descended from caveman & ponytail

FAQ

No — terse ≠ incomplete. The rules cut words around the facts, never the facts: the fix, the gotcha, the caveat all stay. In the 20-task benchmark every RDXmin answer was verified correct.