copcache

copcache is a command for coding agents from orrzxz/Houdini21MCP. It costs 0 tokens per session (276 once invoked), scanned A, original, MIT.

A command for managing the internal Copernicus node cache in Houdini, a tool for creating procedural 3D graphics. It can control cache output, clear the cache, and set how much graphics-card memory its buffers may use.

In plain words
What is it for?
Use it to clear the Copernicus cache, reduce its graphics-card memory allocation, run quietly, or show extra command output.
Why use it?
It helps when cached data or graphics-card memory affects Houdini's processing, especially when other programs need that memory or cached nodes need to be unloaded.

Command

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.

agentmods
npx agentmods add commands/orrzxz/houdini21mcp/copcache
Clone the repo
git clone --depth 1 https://github.com/orrzxz/Houdini21MCP

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.

agentmods badge for copcache

README.md
[![agentmods](https://agentmods.dev/badge/commands/orrzxz/houdini21mcp/copcache.svg)](https://agentmods.dev/commands/orrzxz/houdini21mcp/copcache)
Your own site
<a href="https://agentmods.dev/commands/orrzxz/houdini21mcp/copcache"><img src="https://agentmods.dev/badge/commands/orrzxz/houdini21mcp/copcache.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00276
Opus 5 $0.00000 $0.00138
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00028

Measured 5d ago against content hash 17ef9d837a97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copcache 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 5d 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.

houdini/scripts/python/houdinimcp/docs/commands/copcache.md · 39 lines

What it actually says

#type: hscript

= copcache =

"""Manipulates the internal Copernicus node cache."""

:usage: copcache [-q|-v] [-c] [-g <<vramratio>>]

@options

-q: Quiet mode. Performs the command with no output.

-v: Verbose mode. Outputs extra information.

-c: Clear the COP cache. Every loaded COP attempts to unload itself. This includes in-use COPs, which might trigger recooking.

-g <<vramratio>>: Sets the ratio of VRAM to be used by the COP OpenCL buffers. When this limit is reached the buffers will be swapped to the CPU, avoiding running out of VRAM. However, on failure to allocate VRAM buffers are also flushed, so usually this is not required. It can be necessary to reduce it to make Copernicus keep more VRAM free for other concurrent programs.

@related

  • [texcache|Cmd:texcache]
  • [geocache|Cmd:geocache]
  • [objcache|Cmd:objcache]
  • [opunload|Cmd:opunload]
  • [opunload|Cmd:copcache]
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.

  1. 5d ago First seen · 39 lines · 0 tokens per session scan A 17ef9d837a97

Subscribe to this mod's changes

copcache is a command published in the GitHub repository orrzxz/Houdini21MCP (11 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 276 tokens. 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.