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 michielhdoteth/squish-memorynpx agentmods add plugins/michielhdoteth/squish-memory/claude-codegit clone --depth 1 https://github.com/michielhdoteth/squish-memoryGrade A, and why
squish-memory 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": "squish-memory",
"version": "1.6.0",
"description": "Persistent memory system for Claude Code via Squish CLI - remembers conversations, injects context, auto-captures tool results",
"author": {
"name": "4M Labs",
"url": "https://github.com/4m-labs"
},
"homepage": "https://github.com/4m-labs/squish-memory",
"license": "MIT",
"keywords": ["memory", "persistence", "context", "squish"],
"skills": "./skills/",
"hooks": "./hooks/hooks.json",
"mcpServers": "./.mcp.json",
"userConfig": {
"squish_project": {
"type": "string",
"title": "Squish Project Path",
"description": "Path to the Squish project directory",
"default": "."
}
}
}
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 · 24 lines scan A e915d7e2fc3b
squish-memory is a plugin published in the GitHub repository michielhdoteth/squish-memory (11 stars, last pushed 4d 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 2026-08-30.
Other plugins, from other repositories
knowl
Persistent memory for coding agents that retires a fact when a later one replaces it.
knowl
Persistent memory for Claude Code. Facts are typed, sourced, and retired when they change, so a query returns the current answer rather than every answer it has ever held. Local SQLite in your repository — no API key, nothing uploaded.
claude-code-plugin
Prismer Evolution — cross-agent learning network. Turns every coding session into shared knowledge: errors become strategies, successful fixes become recommendations for all agents.
tree-ring-memory
Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.
hipocampus
Persistent agent memory that survives across sessions — auto-compacting 3-tier memory with hybrid search. Your agent remembers what it learned, decided, and built.
titen
Evidence-grounded collaborative memory for coding agents.