Baton
Pass the baton. Conduct the fleet.
Baton turns Claude Code into the conductor of a fleet of coding LLMs — paid cloud
CLIs, free CLIs, and local models on your own machines. You hand each task to the
right agent (pass the baton), and Baton tracks what they did, what it cost, what
you decided, and what you learned. Built on
claude-octopus as the dispatch layer
(recommended companion plugin, not a hard dependency).
Status: v1.2.0-rc.6 — the Fleet Conductor release (capability routing, cost-optimization,
Grimdex, plugin packaging + MCP server). MIT licensed. An early/experimental personal project, shared in the hope it's
useful — not a turnkey product.
📖 New here? Read these
Install (Claude Code plugin)
claude plugin marketplace add Ryfter/baton
claude plugin install baton@ryfter
Commands surface as /baton:<command> — e.g. /baton:fleet doctor, /baton:route, /baton:idea.
Features
Each feature has a one-line "what it does"; the link goes to its full design spec.
- Automatic usage tracking — every AI dispatch is logged with time, cost, and token
counts to a journal, plus a catalog of each model's strengths and pricing.
Commands:
/baton:log-routing, /baton:consolidate-routing.
- Live web dashboard — a browser view at
http://localhost:8765 showing real-time
activity, today's spend, a model leaderboard, and controls to stop local models. Runs
fully offline. (spec)
- A dispatchable fleet of AI models — one registry of paid CLIs, free CLIs, and
local models, all callable from a single command. Adding a model is a few lines of
config. Commands:
/baton:fleet doctor|list|test.
(spec)
- Cross-machine fleet — pull models running on other machines into the fleet over
a private network (Tailscale), so a beefier desktop's local models are usable from your
laptop.
- Job tracking with phases — track a unit of work from research → design → code →
review, each job in its own folder with a brief, a phase log, and captured lessons.
Commands:
/baton:job-start, /baton:job-status, /baton:job-list, /baton:job-phase, /baton:job-resume, /baton:job-lesson.
(spec)
- A searchable knowledge base — your lessons and decisions become a meaning-based
(semantic) search index, fully local — no cloud, no cost. Commands:
/baton:kb-index,
/baton:kb-search. (spec)
- Multi-model research ensembles — ask one question to several models at once and
get a single synthesis of where they agree, differ, and what's uniquely useful.
Commands:
/baton:ensemble, /baton:research.
(spec)
- Six Thinking Hats — examine a question from six fixed angles (facts, feelings,
risks, benefits, creativity, process), then a synthesized conclusion. Command:
/baton:six-hats.
(spec)
- LLM Council — a two-round deliberation where models answer, then refine after
seeing each other's answers; Claude chairs the verdict. Command:
/baton:council.
(spec)
- Parallel code implementation — turn a finished spec into working code: slice it
into independent tasks, build them concurrently in isolated repo copies, then merge
with conflict detection. Commands:
/baton:code-decompose, /baton:code-parallel, /baton:code-merge.
(spec)
- Multi-project portfolio — one screen showing cost, active jobs, decisions, and
last activity across every project you've worked on, with per-project drill-in.
(spec)
- Live ensemble cockpit — watch a multi-model run unfold in the dashboard: each
model's status, duration, and partial answer appear the moment it finishes.
- A self-improving decision log — every significant choice is captured (decision,
alternatives, reasoning); you attach outcomes, and proven patterns roll up into
per-project and cross-project guidance. Commands:
/baton:decision-feedback,
/baton:consolidate-decisions, /baton:project-init. See the Decision log.
