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.
/plugin marketplace add munhq/distilnpx agentmods add plugins/munhq/distil/plugingit clone --depth 1 https://github.com/munhq/distilGrade 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 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 First seen · 19 lines scan A fdd761ef53f1
distil is a plugin published in the GitHub repository munhq/distil (1 stars, last pushed 3d ago), with no licence file. 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
jcodemunch-mcp
Token-efficient retrieval MCP servers for code, docs, and tabular data.
skillreaper
Measure how much of the context your agent loads it ever actually uses - then prune the rest.
skillreaper
Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.
slopgent
Shape the agent's own replies so they are honest about what ran, action-first, and plain — without dropping load-bearing precision.
context-compress
MCP server and hook toolkit that compresses responses and keeps explicitly indexed output searchable.
pdfcompress
Compress and verify local PDFs while preserving text and vector content.