🎩 You're Invited:Meet the Socket team at Black Hat in Las Vegas, August 3-6.RSVP
Sign In

sipcode

Package Overview
Dependencies
Maintainers
1
Versions
47
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

sipcode - npm Package Compare versions

Comparing version
1.6.11
to
1.6.12
+10
-3
package.json
{
"name": "sipcode",
"version": "1.6.11",
"description": "Sip your tokens. Don't gulp them. — Unified token optimization for AI coding agents.",
"version": "1.6.12",
"description": "Sip your tokens, don't gulp them. Keep Claude Code's context clean: drift detection, re-read dedup, integrity scoring, AST-aware reads, and 15 MCP tools for Claude Desktop.",
"keywords": [
"claude-code",
"claude-desktop",
"ai-coding",
"token-optimization",
"context-engineering",
"drift-detection",
"context-rot",
"mcp",
"ast",
"cursor",
"cli",
"context-window",
"cost-reduction"
"cost-reduction",
"reliability"
],

@@ -14,0 +21,0 @@ "homepage": "https://github.com/Anuj7411/sipcode",

<div align="center">
<a href="https://anuj7411.github.io/sipcode/"><img src="https://raw.githubusercontent.com/Anuj7411/sipcode/main/docs/brand/icon/icon-color.png" alt="Sipcode" width="120" /></a>
# Sipcode
**Sip your tokens — don't gulp them.** Keep Claude Code's context clean: fewer tokens spent, sharper answers, and the savings measured so you can trust them.
**Sip your tokens, don't gulp them.** Keep Claude Code's context clean: fewer tokens spent, sharper answers, and the savings measured so you can trust them.

@@ -11,4 +13,5 @@ ### [**Visit the site →**](https://anuj7411.github.io/sipcode/) · [npm](https://www.npmjs.com/package/sipcode) · [benchmark methodology](benchmark/METHODOLOGY.md) · [changelog](CHANGELOG.md)

[![License: MIT](https://img.shields.io/badge/License-MIT-0A0A0A.svg)](LICENSE)
[![Tests](https://img.shields.io/badge/tests-1104%20passing-5B4FCF)](#)
[![Tests](https://img.shields.io/badge/tests-1247%20passing-5B4FCF)](#)
[![Benchmark](https://img.shields.io/badge/corpus%20median-62.6%25-5B4FCF)](benchmark/METHODOLOGY.md)
[![MCP tools](https://img.shields.io/badge/MCP%20tools-15-5B4FCF)](docs/MCP.md)

@@ -227,5 +230,5 @@ </div>

## MCP tools (13, for Claude Desktop & Claude Code)
## MCP tools (15, for Claude Desktop & Claude Code)
**Meter (read-only):** `get_sipcode_info`, `verify_sipcode_impact`, `list_recent_sessions`, `audit_latest_session`, `get_project_manifest`, `estimate_task_cost`, `get_agent_score`, `get_session_stats`, `get_proxy_stats`, `get_proxy_status`, `get_drift_report`
**Meter (read-only):** `get_sipcode_info`, `verify_sipcode_impact`, `list_recent_sessions`, `audit_latest_session`, `get_project_manifest`, `estimate_task_cost`, `get_agent_score`, `get_session_stats`, `get_proxy_stats`, `get_proxy_status`, `get_drift_report`, `get_today_summary`, `forecast_monthly_spend`
**Valve control (writes settings.json):** `install_proxy`, `uninstall_proxy`

@@ -264,6 +267,9 @@

| `sipcode stats` | Cross-session analytics |
| `sipcode today` | Daily dashboard: spend so far + comparison to your adaptive 30/14/7/3 day median |
| `sipcode forecast` | Projected month-end spend with confidence band + last-month comparison |
| `sipcode trend <metric> --since <NNd>` | Single-metric time series: output-ratio, cost-per-session, or recoverable-tokens-per-session |
| `sipcode estimate "<task>"` | Per-model cost prediction |
| `sipcode score` | Agent-friendliness audit + badge |
| `sipcode drift` | Flag context/cost regressions vs your baseline (silent unless it regressed) |
| `sipcode benchmark` | Reproducible corpus (`--hardest`, `--vs-rtk`) |
| `sipcode benchmark` | Reproducible corpus (`--hardest`, `--vs-rtk`, `--live`) |
| `sipcode receipt` | Shareable PNG of a session's savings |

@@ -270,0 +276,0 @@ | `sipcode hygiene` | Read-once rules + context-pressure hooks |