agentleFS
Sign inStart free
mihaimurra001mihaimurra001/preConfigProject/.agents/skills/headroom/SKILL.md

headroom

Skill1 starsChanged 2 months agoMITView on GitHub

Use to compress large tool outputs, command logs, bulky JSON data, and files, or inspect context compression statistics.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When running commands that produce massive stdout/stderr (e.g.

    line 17
  2. Very specific:

    Check token efficiency and savings with headroom_stats.

    line 18
  3. Distinctive:

    Never let runaway logs consume the context window — compress early.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Headroom: Context & Token Compression

Headroom reduces input token consumption by 20–90% across coding sessions, keeping your context window focused and preventing prompt-bloat:

1. Core Capabilities

  • SmartCrusher: Compresses large JSON payloads and tabular dumps while preserving schema integrity and key values.
  • CodeCompressor: Compresses repetitive source code, declarations, and AST structures without losing function signatures.
  • Kompress-v2-base: Compresses verbose prose, system logs, and shell output while keeping critical lines (e.g. FATAL, ERROR, stack traces) byte-for-byte intact.
  • CCR (Context Compression Retrieval): Caches full uncompressed content locally; call headroom_retrieve whenever the full raw text is required.

2. Best Practices for Coding Agents

  1. When running commands that produce massive stdout/stderr (e.g. test suites, build logs, git diffs > 500 lines), pass them through headroom_compress or examine compressed summaries.
  2. Check token efficiency and savings with headroom_stats.
  3. Never let runaway logs consume the context window — compress early.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free