<p align="center" <img src="supertool-banner.webp" alt="SuperTool — cut your Claude Code bill by 50%" width="900" </p
supertool
Cut your Claude Code bill by 50%. git-status, but it tells you what to do next.
Saves tokens. Saves money. Saves turns. Works the same in interactive sessions and autonomous runs — humans pair-programming with Claude Code use it every day, not just Kevin-style headless agents. One Python file, zero deps, Python 3.9+.
Why • Four pillars • Receipt • Batching • Parallel • Input forms • Validators • Expand it • Install
# 7 ops, 1 round-trip, parallel where safe
supertool 'read:src/Module.py' 'read:src/Auth.py' 'grep:TODO:src/:20' 'map:src/'---
Why
Hammer in 2026. Claude Code's default toolbelt is 1995 unix: cat one file, grep one pattern, git status returns 200 bytes of porcelain. Every tool call re-sends the entire conversation cache — system prompt, CLAUDE.md, rules, every prior turn — at 10% of input price. Read 7 files? Pay that prefix 7 times. Run git status then realize you needed ahead/behind too? Pay it twice for one decision. The bill compounds turn over turn.
Drill in 2026. supertool gives the agent variants that pack the next question into the current call:
- git-status — branch + tracking + ahead/behind + dirty files + open MR/PR + suggested next step. One call, decision ready.
- gl-mr:NUMBER / gh-pr:NUMBER — full MR/PR dashboard: branch, pipeline, reviewer, approval, diff stat, per-file name-status (A/D/R/M) list, comments. Replaces 4-5 glab/gh calls.
- gl-mrs — MR triage board: your open MRs + per-MR pipeline status + which already have a watch poller running + an actionable footer. Pairs with watch to auto-watch every failing MR.
- claude-log-summary:UUID — model, duration, tool calls, tokens, cache hit %, errors-by-tool. Audit your own runs.
That's a sample. supertool ships ~40 ops out of the box (built-ins + gitlab / github / git / claude-log presets) — add your own and you're past 60 fast.
The variant is the lever. A turn saved isn't free time — it's a cached prefix you didn't re-pay.
Four pillars
| Pillar | What it does | | ---------------- | -------------------------------------------------------------------------------- | | Right tool | Variants pack state + guards + next-step into one call. Less to remember. | | Batched | 7 ops, 1 round-trip. The cached prefix gets re-paid once, not seven times. | | Parallel | Read-only ops in a batch run concurrently — ~3-5× faster on cold I/O. | | Expandable | Add a custom op in 4 lines of JSON. Presets ship gitlab, github, git, claude-log. |
Receipt — the bulldozer math
| Mode | Cache reads | Output | Turns | Savings | | ------------------------ | ----------: | -----: | ----: | ---------: | | Hammer (no batching) | 436K | 1,400 | 10 | — | | supertool | 133K | 750 | 3 | 50% | | Pre-computed + supertool | 85.5K | 600 | 2 | 56% |
50% fewer tokens, 3-4× faster wall time. Fewer turns = fewer prefix re-reads. Multiply by task count and team size — the bill cut is real.