Context engineering, explained by an operator
You're not prompt engineering. You're steering. Here's what context engineering actually means when you're running twenty-plus apps and thirty terminals at once.
6 min readcitizencapet
Blog.
Field notes on agentic workflows, context engineering, and the plumbing that makes long-running Claude Code sessions actually useful.
Training the agent to think like you
The point of a memory layer isn't search. It's reflex transfer. Every steering decision you captured becomes the agent's starting position on the next problem.
6 min readcitizencapet
Why local-first still matters for developer tools in 2026
Offline. On-device. No servers. In 2026 it sounds nostalgic. Here is the case for why local-first is the only responsible posture for tools that read your code and your conversations.
5 min readcitizencapet
A field guide to organizing thousands of AI coding sessions
You have 1,200 sessions and climbing. Aliases, tags, collections, pins, notes. Here is the mental model that actually scales, with examples from a real power-user setup.
5 min readcitizencapet
Piping a past Claude Code session into a new one
The feature nobody else has: `recall context <id> | claude` hands a full earlier conversation to a fresh Claude session as starting context. Here is the tactical guide.
4 min readcitizencapet
Process-tree correlation: matching VS Code terminal tabs to Claude Code sessions deterministically
Timing windows are how you lose data. Walking the process tree is how you do it deterministically. Here is the algorithm inside the Claude Recall VS Code extension (v0.7).
5 min readcitizencapet
The 1,000 line terminal scrollback limit in VS Code, Cursor, and Windsurf
VS Code, Cursor, and Windsurf all cap integrated terminal scrollback around 1,000 lines. A real Claude Code session blows past that in ten minutes. Here is what actually breaks and how to work around it.
4 min readcitizencapet
Thirty terminals, twenty apps: structuring a multi-repo Claude Code workflow
You do not have one project open. You have twenty. You do not run one Claude session. You run thirty. Here is the shape of the workflow that does not collapse under that load.
5 min readcitizencapet
Model Context Protocol, explained by the thing we built on it
MCP is Anthropic's open protocol for letting models call native tools. Here is what it does, why it matters, and a worked example using Claude Recall's six read-only tools plus the seven write tools we shipped in v0.13.
4 min readcitizencapet
Where Claude Code actually stores your sessions
Claude Code writes every conversation to ~/.claude/projects/ as JSONL. Here is exactly what lives there, what each file contains, and why it is useless by default.
5 min readcitizencapet