claude-code

b.com/DioxusLabs/blitz for the parsing/layout and then getting that rendered with kitty. So anything Bitz supports this supports. As part of the npm package I ship an LLM skill that tells an LLM how to use this, but what I'm really ultimately aiming for here is to have this rendered inline in Claude Code. However, [CC doesn't yet support image protocols](https://github.com/anthropics/claude-code/issues/2266), but once it (inveitably?) does I would update the skill so that "create a plan in html and display it with kittyhtml" would have the plan (or whatever) rendered directly in your CC session.

oject where you want to run agents. fleet bd create records the cwd where the task was created, and the agent is spawned in that same location. beads is a git-backed issue tracker that gives agents a shared queue of tasks with dependencies, statuses, and priorities — so multiple sessions can claim, work on, and hand off tasks without stepping on each other. - fleet supports 3 coders: claude, agy (Antigravity), and codex, and adding a new one is a matter of minutes. I tested claude extensively, agy briefly, and I don't have a subscription for codex — so it's implemented but not tested yet. - fleet can spawn as many coding agents as you like. fleet config set max_concurrent=10 and keep adding tasks with fleet bd create --title "..." --description "...", or with a specific coder/model per task: fleet bd create --coder agy --model opus --title "..." --description "...". When I started, 3 parallel coding sessions were enough for me; now I can manage 10+. The reason for max_concurrent=3 default is to not hit session limits. - fleet has few useful cli command to help with navigation: -- fleet tasks - display tasks in progress, what coder is used, what context consumption is -- fleet task <task-id> log | plan | knowledge -- fleet config show | set This works nicely for me. fleet also pairs well with a spec-driven approach: https://news.ycombinator.com/item?id=48231575. Tokens are the bottleneck now — I have a few Claude subscriptions and rotate between them when one is exhausted. I also cleaned up all my plugins, skills, and CLAUDE.md files to stop polluting the context — I found that some plugins were installed multiple times and loading the same skills twice, doubling their token cost.

at loop: a shell loop calling claude -p "take next task", with context cleared automatically at the end of each session. This works fine for a single worker. Scaling beyond one agent needs a few extra pieces: - A proper queue. This is what beads provides — dependency-aware, atomic claims via bd ready and bd update --claim, so two workers don't grab the same task. - A channel back to the human. Also handled by beads: bd update <id> --status blocked --notes "QUESTION: <one-line question>" parks the task and surfaces the question without halting the rest of the fleet. - Session memory. Because each claude -p invocation starts with a fresh context, the agent has to write down what it has done, what it plans to do, and any related notes — either into beads itself (status, notes, dependencies on the issue) or to disk — so the next session can pick up cleanly after a restart. With these components in place, we can spawn many claude workers pulling from tasks from beads db, asking questions, adding tasks to db, storing progress and final artifacts to disk. AMD describe this pattern in their amazing issues description https://github.com/anthropics/claude-code/issues/42796. It took me some time to figure out how this suppose to work.