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/coldzero94/cold-frameWrote 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/coldzero94/cold-frame/plugin)<a href="https://agentmods.dev/plugins/coldzero94/cold-frame/plugin"><img src="https://agentmods.dev/badge/plugins/coldzero94/cold-frame/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/coldzero94/cold-frame/plugin"><img src="https://agentmods.dev/badge/plugins/coldzero94/cold-frame/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
coldframe 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 1mo 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": "coldframe",
"displayName": "Coldframe Memory",
"version": "0.1.0",
"description": "Local-first, ownable memory for Claude Code — automatic recall + capture, one SQLite file you own. No API key.",
"author": { "name": "Coldframe" },
"license": "Apache-2.0",
"keywords": ["memory", "recall", "local-first", "sqlite"],
"hooks": "./hooks/hooks.json",
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 1 skill, 2 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 58 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.
- 1mo ago First seen · 12 lines scan A 3904c2a7ef0c
coldframe is a plugin published in the GitHub repository coldzero94/cold-frame (0 stars, last pushed 4d ago), 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 2026-08-31.
Other plugins, from other repositories
plur
Persistent, local-first shared memory for AI agents. Corrections, preferences, and conventions persist across sessions, tools, and machines — stored as plain YAML on your disk, with zero-cost local search.
remnic
Universal memory for AI agents — automatic recall, observation, and cross-agent knowledge sharing.
alice-memory
Local-first memory for Claude Code: an MCP server and a SessionStart brief on one SQLite file.
alicememory marketplace
Alice Memory plugins for Claude Code.
vibebox
Local-first structured memory middleware for Claude Code and other AI coding agents.
forkmind
Local-first LLM branching, debugging & context offloading. Treat AI context windows like a Git repo — capture, branch, regression-test LLM calls as a DAG, and archive context as encrypted, restorable capsules. Teaches Claude when and how to drive ForkMind.