session-primer

Bootstrap session context with Serena memories, claude-mem observations, and git state.

Updated Apr 14, 2026
One-click install
npx skills add https://github.com/jrmatherly/spacebot --skill session-primer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: session-primer
Source: https://github.com/jrmatherly/spacebot/tree/main/.claude/skills/session-primer
Command: npx skills add https://github.com/jrmatherly/spacebot --skill session-primer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

New Claude Code sessions often start with missing project context, stale memories, or fragmented cross-session continuity which forces the assistant to re-learn or guess prior work; this primer automates restoring that context so work can continue immediately.

Core Features & Use Cases

  • Activate Serena project context: runs the Serena MCP activation and reads the five canonical project memories (overview, structure, style, suggested commands, task checklist).
  • Retrieve cross-session continuity: scans the claude-mem CMEM header and fetches recent observations or performs semantic searches to recover last work and decisions.
  • Assess workspace state: runs git status/log/branch checks and inspects openspec change directories to determine the working-tree and active tasks.
  • Domain identification & recommendations: infers the task domain (spacebot-dev, spacedrive-dev, spaceui-dev, cluster-context, etc.) and recommends the appropriate domain skill without preloading it.
  • Resilience patterns: documents the Claude-Mem read gate behavior and includes read strategies (explicit limits) to avoid truncated reads.

Quick Start

Prime the session to load Serena memories, retrieve recent claude-mem observations, assess git state, and produce a concise readiness report.

Frequently Asked Questions about session-primer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I restore project context when starting a new Claude Code session?

To restore project context in a new Claude Code session, prime the session by activating Serena memories, scanning claude-mem observations, and running git status checks to produce a concise readiness summary.

What is the best way to load cross-session memories and git state before development?

Loading cross-session memories and git state requires retrieving claude-mem observations, reading Serena project memories, and checking git branches to determine the active working-tree state before development.

How does claude-mem integration work for retrieving past session observations?

Claude-mem integration retrieves past session observations by scanning the CMEM header and fetching recent records, while respecting the file-read gate by using explicit read limits to avoid truncated reads.

Can I use Serena MCP to bootstrap project context and memories automatically?

You can use Serena MCP to automatically bootstrap project context by activating it to read five canonical project memories, including overview, structure, style, suggested commands, and task checklists.

Why does context feel stale when resuming a Claude Code session after a long gap?

Context feels stale after a long gap because new sessions start with missing project continuity and fragmented memories, requiring a primer to recover last work and decisions automatically.

Are there limitations when reading large claude-mem observation files during session bootstrapping?

Yes, reading large claude-mem observation files faces limitations from the file-read gate, which can truncate reads, so you must apply explicit read limits to avoid truncated output during session bootstrapping.