oimiragieo/agent-studio

token-saver-context-compression

Search-aware context compression workflow for agent-studio. Use pnpm hybrid search + token-saver compression, then persist distilled learnings via MemoryRecord.

First seen Feb 19, 2026

Installation

$ npx skills add oimiragieo/agent-studio --skill token-saver-context-compression

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from oimiragieo/agent-studio · top by installs.

npx skills add oimiragieo/agent-studio

Browse all from oimiragieo/agent-studio

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 40
Default branch main
Open issues 501
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 842 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 90 installs

SKILL.md

Token Saver Context Compression

Alias for context-compressor. Provides context window optimization by compressing large payloads before reasoning.

When to Use

  • Context approaching budget limits (80K+ tokens)
  • Large file reads that can be summarized
  • Multi-agent pipelines with context handoff
  • Any scenario where context-compressor would be used

Activation

Activate this skill when compression-reminder.txt appears or when the active context is approaching the 80K token pressure threshold.

Usage

Skill({ skill: 'context-compressor' });

This skill exists as a named alias so agents referencing token-saver-context-compression in their skills arrays resolve correctly. The implementation lives in context-compressor.