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.
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.
git clone --depth 1 https://github.com/headroomlabs-ai/headroomWrote 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.
[](https://agentmods.dev/plugins/headroomlabs-ai/headroom/headroom-agent-hooks)<a href="https://agentmods.dev/plugins/headroomlabs-ai/headroom/headroom-agent-hooks"><img src="https://agentmods.dev/badge/plugins/headroomlabs-ai/headroom/headroom-agent-hooks/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.
<a href="https://agentmods.dev/plugins/headroomlabs-ai/headroom/headroom-agent-hooks"><img src="https://agentmods.dev/badge/plugins/headroomlabs-ai/headroom/headroom-agent-hooks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
headroom 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 yesterday.
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.
What it actually says
{
"name": "headroom",
"version": "0.41.0",
"description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",
"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",
"hooks",
"claude-code",
"copilot-cli"
]
}
What it installs
The manifest is a name and a version. 2 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
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.
- yesterday Changed ac4b25e696ad
- 9d ago Changed 965574d0261d
- 19d ago Changed 20fa09c38aa7
- 20d ago Changed 394aa9a5744e
- 24d ago Changed 3dd1a7db1b9f
- 1mo ago Changed 54d764ca00d6
- 1mo ago First seen · 18 lines scan A 14cfaed4e274
headroom is a plugin published in the GitHub repository headroomlabs-ai/headroom (75,453 stars, last pushed today), 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 2026-08-30.
Other plugins, from other repositories
aidd-pm
Product backlog artifacts, refinement, Product Briefs, Epics, User Stories, Tasks, Spikes, Defects, requirements, and specs.
promptsmith
Prompt & context engineering for agents — /sharpen rough requests, /forge-agent reusable system prompts, /lens to review through expert lenses (or grade a prompt against a rubric with --grade), and /orchestrate multi-domain builds across a 20-agent specialist gallery. Eval-backed. Zero dependencies, no API keys, model.
shariful-claude-plugins marketplace
Claude Code plugins by Shariful Islam — token inspection and context optimization tools.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.