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/munhq/distilWrote 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/munhq/distil/plugin)<a href="https://agentmods.dev/plugins/munhq/distil/plugin"><img src="https://agentmods.dev/badge/plugins/munhq/distil/plugin/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/munhq/distil/plugin"><img src="https://agentmods.dev/badge/plugins/munhq/distil/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
distil 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 7d ago.
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": "distil",
"description": "Skills and MCP server for context optimization \u2014 decide whether compressing an agent's context pays for the prompt cache it invalidates, and compress it when the answer is yes. Bundles the distil MCP server so install wires everything in one step.",
"version": "0.3.4",
"author": {
"name": "munhq"
},
"homepage": "https://github.com/munhq/distil",
"repository": "https://github.com/munhq/distil",
"license": "MIT",
"keywords": [
"context",
"tokens",
"prompt-cache",
"compression",
"mcp"
]
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 81 tokens a session between 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.
- 7d ago Changed 10e7e8dd1de3
- 1mo ago First seen · 19 lines scan A fdd761ef53f1
distil is a plugin published in the GitHub repository munhq/distil (1 stars, last pushed 7d ago), licensed MIT. 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 2026-08-31.
Other plugins, from other repositories
headroom
Headroom startup hooks for Claude Code and GitHub Copilot CLI.
token-optimizer
Context-window optimization tools (caching, compression, smart file tooling) for the Gemini CLI.
linggen
Linggen for Claude Code — two local MCP servers, each tool served in one place: durable cross-host memory from ling-mem, browser control in your own Chrome and logged-in X reads from the Linggen engine. Per-turn memory recall built in, and /linggen:config points this host at a Linggen on another machine. Installs its…
token-optimizer
Audit, fix, and monitor Claude Code context window usage. Find the ghost tokens.
mcp-recall
Context compression and persistent retrieval for Claude Code.
zc-ctx
Secure memory + persistent context + skill-admission gate for Claude Code. HMAC-chained toolcalls + outcomes, per-agent HKDF subkey isolation, Postgres RLS, work-stealing task queue, MemGPT-style persistent memory, Agent Notebook Model (Read→Summary redirect), and v0.26.0+ Anthropic-style filesystem skills with AST.