I'm rethinking the processes and frameworks behind productivity and operational efficiency in the age of AI. I write about the ideas here, and ship the tools that fall out of them under Framework Reboot.
Done items leave SEQUENCE.md while their records remain available. The backlog stays shorter as work is finished.
Deferred and cancelled work leaves SEQUENCE.md too. The generated backlog contains only open work, and retired identities stay taken.
A Python runtime now manages work records and generates the backlog. The chain has sixteen skills, including a migration path for existing projects.
Review agents now label every finding by confidence instead of quietly dropping the uncertain ones. Two conversational skills join the chain, one agent leaves it, and a backlog can now be shared across repos.
Repair can now survey an older backlog before its namespace or work root exists. The plan includes the setup it needs, with no writes until you approve it.
CommandLane is not shipping. The hardest part of it now stands on its own: a Python sidecar supervised by a Tauri desktop app, published as a template.
A Claude Code plugin that writes down the instructions I was otherwise retyping every session.
A changelog note: external agents now install in one click, and you can keep several on hand and switch between them mid-flow.
Most teams already have the tools they need. What they are missing is a shared model of the work.
The first stable release. State snapshots are now content-addressed, with a typed schema for work items and a real diff engine.
The integrations between your tools are where operational knowledge quietly lives, and quietly rots.
A short note on why a keyboard-first command surface belongs in this family.
Framework Reboot is a bet that the frameworks I inherited for managing work weren't built for a world with AI in the loop.
Connectors are now fully typed, with retry and backoff on every bridge. One breaking change to the invoke API.
A quick changelog note: the command palette now triggers multi-step actions instead of only navigating.
A diagnostic for knowing when a productivity system has quietly stopped serving you, and what to do about it.
Turning the OPERA Operations layer from an idea into a Notion and agents integration you can actually run.
PARA organized my digital life for years. Here is why the arrival of AI meant even a system that good had to grow an operations layer.