Skip to content
Agentmart
Submit a tool

rtk-compress

Compress raw text, massive stack traces, huge JSON payloads, or verbose logs before sending into context.

Skill by terenceooi99

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/terenceooi99-rtk-compress

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Compress raw text, massive stack traces, huge JSON payloads, or verbose logs before sending into context. Activate when the user types /rtk-compress, /headroom-compress, "compress logs", "compress json", or asks to condense a large payload to save prompt tokens.

Use cases: agent-building

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/rtk-compress

What's inside

Skill name
rtk-compress
Description
Compress raw text, massive stack traces, huge JSON payloads, or verbose logs before sending into context. Activate when the user types /rtk-compress, /headroom-compress, "compress logs", "compress json", or asks to condense a large payload to save prompt tokens.
License
MIT
Instructions
10 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# RTK / Headroom Context Compression (/rtk-compress)

Condense heavy textual data, build logs, stack traces, or deep JSON payloads to minimize LLM prompt token consumption while preserving critical semantic context.

## Compression Strategies
1. **JSON Payloads:** Strip null/empty fields, trim large redundant arrays to representative samples, and collapse metadata headers.
2. **Build / Test Logs:** Retain only the failed assertions, error messages, root stack traces, and exit codes; strip repetitive passing progress bars.
3. **Large Files / Dumps:** Use Headroom CCR (Compress-Cache-Retrieve) pattern or extract structural outline instead of full raw content.

From terenceooi99/token-saver-rtk-ide, MIT.

More from terenceooi99/token-saver-rtk-ide

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 29, 2026 (29 days ago)
Last release
Oct 18, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/terenceooi99/token-saver-rtk-ide
Website
open-vsx.org/extension/terenceooi/token-saver-rtk-ide
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from terenceooi99

Cite this page

rtk-compress skill. Agent Mart. https://agentmart.dev/skills/terenceooi99-rtk-compress (last updated 2026-10-24)