What is headroom-skill?

A plugin that adds Headroom's compression helper to a Python or TypeScript app, reducing the size of AI input from tool outputs, logs, JSON, and chat history.

It is for adding message compression to applications that send large results or conversation history to an AI model.

It helps keep large AI requests within context limits and can reduce the amount of input sent to the model without requiring an API key.

headroom-skill — Plugin for Claude Code by headroomlabs-ai/headroom

About the project

Headroom is a library, proxy, and MCP server that compresses tool outputs, logs, files, retrieval chunks, and conversation history before they reach a language model. It helps coding agents use fewer context tokens while keeping the original content available locally when needed. Its catalogue add-ons support using Headroom with agent workflows.

headroomlabs-ai/headroom · 78,940 stars · on GitHub · docs.headroomlabs.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/headroomlabs-ai/headroom

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/headroomlabs-ai/headroom/headroom-skill/github.svg)](https://agentmods.dev/plugins/headroomlabs-ai/headroom/headroom-skill)

Your own site

<a href="https://agentmods.dev/plugins/headroomlabs-ai/headroom/headroom-skill"><img src="https://agentmods.dev/badge/plugins/headroomlabs-ai/headroom/headroom-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/headroomlabs-ai/headroom/headroom-skill"><img src="https://agentmods.dev/badge/plugins/headroomlabs-ai/headroom/headroom-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill cost 76 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

headroom-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/headroom-skill/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "headroom-skill",
  "version": "0.43.1",
  "description": "Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.",
  "author": {
    "name": "Headroom Contributors",
    "url": "https://github.com/headroomlabs-ai/headroom"
  },
  "homepage": "https://github.com/headroomlabs-ai/headroom",
  "repository": "https://github.com/headroomlabs-ai/headroom",
  "keywords": [
    "headroom",
    "skill",
    "token-cost",
    "tool-outputs",
    "context-window",
    "claude-code",
    "codex",
    "copilot-cli"
  ]
}

Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 76 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Skill headroom A 76 tokens

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed 7c14248e39e3
yesterday First seen · 22 lines scan A 2c3fd4c9aa6e

Subscribe to this mod's changes

headroom-skill is a plugin published in the GitHub repository headroomlabs-ai/headroom (78,940 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-05.

Data and AI agent ai anthropic compression context-engineering context-window

headroom-skill next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
headroom-skillheadroomlabs-ai/headroom	Plugin	79k	yesterday	Apache-2.0	A	—	Claude Code
llm-languageSilence-view/llm-language	Plugin	2	4mo ago	MIT	A	—	Claude Code
aidd-telemetryai-driven-dev/framework	Plugin	550	today	MIT	A	—	Claude Code
local-ainaveedharri/benai-skills	Plugin	78	28d ago	MIT	A	—	Claude Code
machine-learning-opsyeaight7/agent-powerups	Plugin	8	1mo ago	Apache-2.0	A	—	Claude Code
ensembleraiyanyahya/ensemble	Plugin	13	5mo ago	MIT	A	—	Claude Code
humanizerblader/humanizer	Plugin	65k	9d ago	MIT	A	—	Claude Code