M0. Foundations — the session loop — Agent Workspace Practice MCP Resource
M0. Foundations — the session loop
is one of 71 resources on the
Agent Workspace Practice
MCP server. Connect the server and your client can attach it as context.
by client
How to attach M0. Foundations — the session loop from your client
- Claude Code Agent Workspace Practice Resource/M0. Foundations — the session loop run in your project directory
- Claude Desktop Agent Workspace Practice Resource/M0. Foundations — the session loop ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Agent Workspace Practice Resource/M0. Foundations — the session loop ~/.cursor/mcp.json
- VS Code Agent Workspace Practice Resource/M0. Foundations — the session loop .vscode/mcp.json
- Zed Agent Workspace Practice Resource/M0. Foundations — the session loop ~/.config/zed/settings.json
- Windsurf Agent Workspace Practice Resource/M0. Foundations — the session loop ~/.codeium/windsurf/mcp_config.json
- Cline Agent Workspace Practice Resource/M0. Foundations — the session loop ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Agent Workspace Practice Resource/M0. Foundations — the session loop ~/.gemini/settings.json
- Grok Agent Workspace Practice Resource/M0. Foundations — the session loop .mcp.json (in your project root)
- ChatGPT Agent Workspace Practice Resource/M0. Foundations — the session loop Settings → Connectors → Advanced → Developer mode
- Claude.ai Agent Workspace Practice Resource/M0. Foundations — the session loop Settings → Connectors → Add custom connector
- LangChain Agent Workspace Practice Resource/M0. Foundations — the session loop pip install langchain-mcp-adapters
Other resources on this server
- Patterns
- 1. Pure roles, composed with project facts
- 2. Classify-then-act, not ask-then-wait
- 3. Make silent failure loud (the dead-man's switch)
- 4. Tier by mechanical impact, not by tone
- 5. Memory points, it doesn't mirror
- 6. Credentials live in one place, never in files
- 7. A cheap hook beats a careful agent
- 8. Audit the workspace like a fitness function
- 9. Context is a budget, not a constant
- 10. A skill is editable weights — never adopt a self-edit without a gate
- 11. A scaffold is a hypothesis — gate it behind a measurable signal
- 12. Loop selection: not everything should be a loop
- 13. Challenge half-formed ideas with a different lens — and hold a samp…
- 14. Delegation is a queue you fill, not work the agent finds
- 15. Price the lane before you migrate it
- 16. A claim carries its provenance, or it is a guess
- 17. One canonical copy, and pointers from everywhere else
- 18. Position is price — a token costs more the earlier you add it
- How they compose
- Evaluation: knowing whether a workspace change helped
- The instrument
- 1. Deterministic checks only, never a judge
- 2. A pass-rate with variance, never a single number
- 3. Five fixture classes, and two of them are the point
- What it costs
- How it connects to the rest
- Where it lives
- Do this
- Measure it
- M1. Canonical knowledge — one source of truth
- The patterns
- M2. Context economics — context is spend
- M3. Verification & oversight — trust through checks
- M4. Safety & permissions — cheap mechanical guards
- M5. Telemetry & cost — loud failure, priced lanes
- M6. Provenance & delegation — sourced claims, mandated work
- Learn the architecture
- Where to start
- The modules
Read from the server itself, by connecting to it and calling resources/list on 24 September 2026.
A listing does not declare its resources, so asking is the only way to know them, and this
is what the server actually offers rather than what its listing claims. Names only are
stored; connect the server for each resource's type and contents.