Pith

GitHub Stars

Status: stable — not actively adding features. Bug fixes welcome via issues.

Token compression hooks for Claude Code. Install once, works in every session, zero config.

bash <(curl -s https://raw.githubusercontent.com/abhisekjha/pith/main/install.sh)

Four hooks attach to Claude Code's lifecycle. Every session, every project, automatically.

• PostToolUse — compresses file reads, bash output, and grep results before they hit context
• UserPromptSubmit — runs /pith commands, enforces token ceiling if set
• SessionStart — restores compression mode, injects cache-locked rules
• Stop — records token usage for status and report

The PostToolUse hook is where most savings happen — file reads alone account for 30–50% of context in a typical coding session.

Runs automatically. No commands needed. Every file read, bash run, and grep gets compressed on the way back to Claude.

Real session numbers:

Read large-service.ts → 1,800 tokens baseline → 210 tokens compressed (−88%)
npm install output → 940 tokens baseline → 80 tokens compressed (−91%)

Control how Claude writes back to you.

/pith → lean: drop filler, short synonyms, fragments OK
/pith ultra → maximum: abbreviate, arrows, tables
/pith precise → tight but full sentences
/pith off → disable output compression

Auto-escalation kicks in as context fills — no manual switching needed:

50% fill → LEAN
70% fill → ULTRA
85% fill → dynamic token ceiling

/pith status → ASCII flow chart — baseline vs compressed vs output + plain-English savings
/pith report → interactive HTML dashboard (auto-refreshes every 30s)

/pith status — token flow chart, compression ratio, cost breakdown

Load only the sections of a file relevant to your current question. Saves re-reading large files.

/focus src/services/auth.ts

Returns the 5 most relevant sections with a structure overview. Works on any file type.

Pull exact function or class definitions without reading the whole file.

/pith symbol src/auth.ts handleLogin → exact 30–50 lines (~95% vs full file)
/pith symbol --list src/auth.ts → all symbols with line numbers

# One-liner
bash <(curl -s https://raw.githubusercontent.com/abhisekjha/pith/main/install.sh)
# From source
git clone https://github.com/abhisekjha/pith
bash pith/install.sh

Hooks install globally into ~/.claude/hooks/. Active in every session from that point on.

Update:

/pith update → git pull + re-sync hooks, commands, settings

Uninstall:

/pith uninstall

All present and functional. Not the daily workflow, but there when you need them.

Estimates against real usage — not against "no system prompt."

Before Pith: Read large-service.ts → 1,800 tokens
After Pith: Read large-service.ts → 210 tokens (−88%)
Before Pith: npm install output → 940 tokens
After Pith: errors + summary → 80 tokens (−91%)

Session from real use:

• 19.9k input tokens (237.9k baseline without Pith)
• 218k tokens saved — 92% compression ratio
• 0ドル.07 actual vs 3ドル.33 without Pith — ×ばつ cost ROI

See BENCHMARKS.md for methodology and raw numbers.

Pith detects the model automatically and applies correct rates. No config needed.

Falls back to Sonnet 4.6 rates if model can't be determined.

Star History Chart

MIT