agentleFS
zedarvateszedarvates/frugal-skills/skills/agent-compression/SKILL.md

agent-compression

Skill1 starsChanged 30 days agoMITView on GitHub

Instructions for the upstream inter-agent binary transport: quantized vectors, shared dictionaries, deltas and repeated-section hashes. Use when repeated machine-facing messages need a compact wire format. Not for human-readable payloads, content compression (universal-compressor), memory compression (agent-intel) or report JSON (ultra-compact).

The file

Files
SKILL.md

agent-compression — inter-agent binary transport

Package scope and prerequisites

This catalog ships instructions, not the executable runtime. Python modules, scripts, local services and optional tools named below must be installed separately from the upstream project. Check their availability before running commands; if they are missing, explain the prerequisite instead of claiming execution or results. The host agent may use model tokens while following these instructions.

Commands, APIs and runtime behavior described below are conditional examples for a compatible upstream installation; they are not evidence of execution in this package.

Purpose

A wire format for messages that agents send to each other. Raw text between agents is treated as the cost driver: vectors are quantized to 4 bits, frequent tokens go through a shared dictionary, a message is sent as a delta against the previous one where possible, and repeated sections are replaced by hashes.

python -m skills.agent_compression.cli compress "message texte"
python -m skills.agent_compression.cli delta "ancien" "nouveau"
python -m skills.agent_compression.cli learn < corpus.txt
python -m skills.agent_compression.cli stats

When NOT to use

  • A human will read the payload — the format is binary, not meant to be read.
  • The payload is a log or a tool output rather than an agent message — use universal_compressor.
  • You want to compress accumulated agent memory — use agent_intel (mem-compress).

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.