Plugins · ppgranger/token-saver

token-saver

Automatically compresses verbose CLI output (git, docker, npm, terraform, kubectl, etc.) to save tokens in Claude Code sessions. 36 specialized processors with content-aware compression.

CLEARED_STATICagent-agnosticv2.7.2

Pipeline results

Coverage

CLEARED_STATIC

Tests run

7 / 8

Portability

Agent-agnostic (works beyond Claude)

Type

Plugins

Tests & results

What the pipeline checked

TestStateResult or reason

eligibilityranall eligibility checks passed

dedupranunique -- no near-duplicate found

clocran23230 code lines / 150 files

secretsranno secret patterns matched

egressran12 lexical match(es) — FLAG-INFO (C-01: semantic analysis deferred to v2)

injectionranno patterns matched (confidence: STANDARD)

required-fieldsranrequired fields present: name, version, description

behaviouraldeferredbehavioural assessment deferred (v1): Python with non-stdlib imports (committed-only policy): [('install.py', 'installers'), ('installers/common.py', 'src')]

What's inside

Components found

commands/token-saver-stats.md

componentlow

docs/benchmarks.md

componentmedium

docs/comparison.md

componentmedium

docs/faq.md

componentmedium

docs/index.md

componentmedium

docs/processors/ansible.md

componentlow

docs/processors/build_output.md

componentlow

docs/processors/cargo.md

componentlow

docs/processors/cargo_clippy.md

componentmedium

docs/processors/cloud_cli.md

componentlow

docs/processors/db_query.md

componentlow

docs/processors/docker.md

componentmedium

docs/processors/env.md

componentlow

docs/processors/file_content.md

componentmedium

docs/processors/file_listing.md

componentlow

docs/processors/generic.md

componentmedium

docs/processors/gh.md

componentlow

docs/processors/git.md

componentmedium

docs/processors/go.md

componentlow

docs/processors/helm.md

componentlow

Coverage

Not assessed

behavioural execution not run
egress patterns logged (FLAG-INFO): 12 lexical match(es)

README

From the repository

# Token-Saver

[![CI](https://github.com/ppgranger/token-saver/actions/workflows/ci.yml/badge.svg)](https://github.com/ppgranger/token-saver/actions/workflows/ci.yml)
[![Coverage](https://img.shields.io/badge/coverage-94%25-brightgreen)](tests/)
[![Python](https://img.shields.io/badge/python-3.10%2B-blue)](https://python.org)
[![License](https://img.shields.io/badge/license-Apache%202.0-blue)](LICENSE)
[![Avg Savings](docs/assets/badge-savings.svg)](docs/processors/)

**Cut your AI coding costs by 60-99% on CLI output — without losing a single error message.**

Token-Saver is a drop-in **context-window optimizer for AI coding assistants**. It compresses the verbose terminal output your agent reads — `git diff`, `pytest`, `npm install`, `terraform plan`, `kubectl`, `docker` — so you spend fewer tokens, stay under your LLM context limit, and get faster, cheaper, more focused responses.

**36 specialized processors** understand the tools you already use — git, pytest, jest, cargo, go, docker, kubernetes, terraform, pulumi, helm, ansible, aws, gcloud, and more. Each one knows exactly what to keep and what to discard: errors, diffs, stack traces, and actionable data stay; progress bars,…

← Back to Plugins