michielhdoteth/squish
skills/squish/SKILL.md
ALWAYS use this skill when working with agents, memory, context, persistence, or AI agent state. Use when the user mentions: 'the agent forgot', 'save this', 'remember that', 'context is lost', 'memory', 'MCP server', 'agent memory', 'persistent memory', 'session context', 'project context', 'recall', 'remember', 'forget', 'cross-session', 'agent decisions', 'store this', 'retain context', 'knowledge retention', 'agent state', 'conversation history', 'project memory', 'team memory'. Also triggers on: building MCP servers, managing sessions, capturing decisions, debugging agent behavior, restoring context. Do NOT use for: general coding, answering questions about unrelated topics, system administration.
$ install --global
skillsauthnpx skillsauth add michielhdoteth/squish squishInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 22, 2026, 6:24 AM165.1s1 file scanned
SKILL.md
- name:
- squish
- description:
- ALWAYS use this skill when working with agents, memory, context, persistence, or AI agent state. Use when the user mentions: 'the agent forgot', 'save this', 'remember that', 'context is lost', 'memory', 'MCP server', 'agent memory', 'persistent memory', 'session context', 'project context', 'recall', 'remember', 'forget', 'cross-session', 'agent decisions', 'store this', 'retain context', 'knowledge retention', 'agent state', 'conversation history', 'project memory', 'team memory'. Also triggers on: building MCP servers, managing sessions, capturing decisions, debugging agent behavior, restoring context. Do NOT use for: general coding, answering questions about unrelated topics, system administration.
Squish: Memory Runtime for AI Agents
Connect once. Remember everywhere. Squish gives ChatGPT, Claude Code, and every AI agent one shared memory through OAuth. Stop re-explaining your project, context, and decisions to every tool.
How Squish Works
Squish is a memory runtime that:
- Captures durable signal from agent sessions automatically
- Stores memories with embeddings, beliefs, and relationships
- Retrieves relevant context across sessions using hybrid search
- Decays unimportant memories over time using Ebbinghaus curves
- Syncs via OAuth cloud when teams need shared memory
Installation
Option A: Cloud (Recommended - connect to ChatGPT/Claude in 2 minutes)
npx squish-memory
squish cloud login
Then configure your agent to use the Squish MCP server.
Option B: Local (fastest, no cloud dependency)
npm install -g squish-memory && squish install --all
MCP Configuration
For OpenCode
Add to your opencode.json:
"squish": {
"type": "local",
"command": ["squish-mcp"],
"enabled": true
}
For Claude Desktop
{
"mcpServers": {
"squish": {
"command": "npx",
"args": ["-y", "squish-memory"]
}
}
}
For ChatGPT (Cloud)
- Go to ChatGPT Settings > Custom MCP Servers
- Server URL:
https://api.squishplugin.dev/mcp - Auth: Bearer Token (get your key from squishplugin.dev)
Tool Reference
When Squish is connected, these tools are available:
| Tool | What it does |
|------|-------------|
| squish_remember | Save content, decisions, preferences, or facts |
| squish_recall | Search or retrieve by query or ID |
| squish_context | Auto-load relevant context for current project |
| squish_stats | Show memory usage and plan status |
| squish_search | Full-text + semantic hybrid search |
| squish_health | Check system status |
| squish_pin | Pin important memories (prevent decay) |
| squish_recent | Recent memories by period |
| squish_forget | Remove single or bulk memories |
Best Practices
When to save a memory
- A decision was made (selecting architecture, choosing a library, agreeing on approach)
- A preference was established (coding style, naming convention, tool preference)
- A constraint was identified (compatibility issue, performance requirement, dependency)
- A failure was diagnosed and fixed (root cause + solution)
- Context was established that will be needed later (project goals, current state)
What NOT to save
- Transient tool output (build logs, test runs, compilation errors)
- Session-only context that is irrelevant after the current session
- Sensitive credentials or secrets (Squish has built-in secret detection)
Memory workflow
1. Session starts -> Squish auto-loads relevant context
2. During work -> Squish captures decisions, fixes, constraints
3. Session ends -> Squish processes new memories, extracts beliefs
4. Next session -> Squish restores context automatically
Squish Cloud
Squish Cloud adds OAuth sync, shared team memory, admin dashboard, and priority support.
| Feature | Local | Cloud Solo ($9/mo) | Cloud Pro ($29/mo) | Team ($99/mo) | |---------|-------|-------------------|-------------------|---------------| | Storage | 10MB | 100MB | 1GB | 10GB | | Users | 1 | 1 | 5 | Unlimited | | OAuth | - | ChatGPT + Claude | All agents | All agents | | Sync | - | Single device | Cross-device | Team sync | | Dashboard | - | Basic | Analytics | Full admin |
Commands
squish remember "content" # Save a memory
squish recall "query" # Search memories
squish context # Load project context
squish stats # Show statistics
squish pin <id> # Pin a memory
squish recent # Show recent memories
squish cloud login # Connect to cloud
squish cloud status # Cloud connection status
Tips for agents using Squish
- Load context at session start: Run
squish_contextto restore project memory - Save decisions explicitly: After making a decision, say "remember this: we chose X because Y"
- Use recall before researching: Before suggesting a new approach, check if Squish has context about previous attempts
- Tag memories: Use tags like
architecture,decision,bug,clientfor better retrieval - Pin critical memories: Pin project goals, architecture decisions, and client preferences
Related Skills
michielhdoteth/squish-memory
development
VerifiedTrustedCommunity
Persistent memory system for Codex with auto-capture, cross-session recall, and context injection.
3SKILL.mdUpdated May 22, 2026
michielhdoteth/plugin/claude-code/skills/squish-memory
tools
VerifiedTrustedCommunity
--- name: squish-memory description: Persistent memory system for Claude Code. Use when you need to store, recall, or search project memories, facts, decisions, and learnings across sessions. Triggers on: remember, recall, memory, forget, search memories, store context, project knowledge, what did we decide, previous conversation. when_to_use: User mentions memory, recall, remember, forget, search memories, store context, project knowledge, prior decisions, past conversations allowed-tools: Bash
3SKILL.mdUpdated May 17, 2026
michielhdoteth/squish-memory
tools
VerifiedTrustedCommunity
Squish - Persistent memory system for AI assistants. Store facts, decisions, context, and notes with CLI and MCP workflows. Score-based decay, no tiers.
3SKILL.mdUpdated Apr 17, 2026
openclaw/taskflow
tools
VerifiedTrustedCommunity
Use when work should span one or more detached tasks but still behave like one job with a single owner context. TaskFlow is the durable flow substrate under authoring layers like Lobster, ACPX, plugins, or plain code. Keep conditional logic in the caller; use TaskFlow for flow identity, child-task linkage, waiting state, revision-checked mutations, and user-facing emergence.
357,764SKILL.mdUpdated Apr 10, 2026