Flight Deck: a worktree-per-agent control panel for Claude Code

The problem in detail

Once a developer tries to go past a single agent session, nothing manages the mechanics: each agent needs its own isolated checkout to avoid clobbering files, each blocks silently waiting for approval or a clarifying question, and there is no single place to see which agent is working, stuck, or finished. So people improvise with a couple of terminal tabs, lose track of who is waiting on them, and fall back to one ticket at a time — the parallel throughput never materialises.

Proposed product

A local terminal UI (single binary, `flightdeck`) that turns each task into an isolated git worktree with its own agent session and shows all of them in one status board. You paste in a task (or point it at an issue), it creates a branch + worktree, launches the agent there, and streams a one-line status per agent: RUNNING / NEEDS YOU / DONE / FAILED. Agents that stop for a question or a permission prompt are surfaced at the top of the board with a desktop notification; you hit a key to jump into that session, answer, and drop back to the board. When an agent finishes, Flight Deck shows the diff and offers a one-key push/PR, then tears down the worktree.

Why now

An open issue on the official Claude Code repo says that when you run several sessions at once there is no way to tell which one is blocked waiting on you — you must check each tab or window by hand — and asks for native OS notifications. A second feature request shows why that gap persists: the existing idle_prompt hook fires after every response, so it cannot distinguish 'I'm done' from 'I need you', and a related issue (#36850) asks for a bell specifically on tool approval. A third-party orchestrator, cmux, has an issue saying its 'Claude waiting' notice is too generic to tell which workspace needs attention, and asks for reason classification. So attention routing across parallel agent sessions is a real, repeatedly reported and still-unsolved need. But the surrounding ground has shifted: several write-ups report Claude Code now ships its own `claude --worktree` flag, and tools such as Claude Squad (reported ~6.8k stars), Conductor, Vibe Kanban, Crystal and Nimbalyst already do worktree-per-agent with diff review and merge. The opening, if there is one, is narrower than the original pitch: accurate per-session state classification and routing, not worktree creation.

Smallest useful version

A CLI + TUI for Claude Code only, on one repo, that does four things: (1) `flightdeck run "<task>"` creates a worktree/branch and starts an agent there; (2) a board listing every live session with detected state by parsing agent output for idle/prompt patterns; (3) notification + hotkey attach when a session is waiting on the human; (4) `d` to view diff, `p` to open a PR, `x` to clean up the worktree. No inter-agent delegation, no cloud, no multi-repo, no scheduling — just isolation plus visibility plus fast context-switching.

Potential ways to charge

• Free open-source core with a paid licence for teams (per-seat, roughly the price of one lunch per developer per month) covering multi-repo and shared boards — noting no purchase signal was found for any tool in this space
• One-off paid desktop app for the macOS/Windows notification layer, priced like a small indie utility, with the CLI free
• Sponsorship or paid support tier if the project gains stars first, following the open-source-tooling pattern the competing tools appear to use
• Consulting or bespoke setup for small teams wanting agent parallelism configured, with the tool as a lead-in

Routes to early customers

• Comment on and subscribe to the exact Claude Code issues requesting native notifications and a tool-approval bell — those subscribers are self-identified sufferers of this problem
• Approach maintainers and users of cmux, which has an open issue asking precisely for per-session reason classification, and offer the classifier as a companion
• Post in the same roundups and newsletters that currently list Claude Squad, Conductor, Vibe Kanban, Crystal and Nimbalyst, positioning against them on attention routing rather than worktrees
• Direct outreach to practitioners who have blogged about losing track between terminal tabs or building their own session monitors

Main risks

• Differentiation is actively weakened by the evidence: the described feature set overlaps almost completely with shipped tools (Claude Squad, Conductor, Vibe Kanban, Crystal, Nimbalyst), and reported built-in `claude --worktree` support absorbs the worktree half outright.
• No willingness-to-pay signal was found at all — no job posting, freelance listing, keyword data or paid review — and the nearest alternatives appear to be free and open source.
• The core technical value depends on classifying state from a noisy upstream signal; the evidence shows the idle_prompt hook fires after every response and that a competitor's notifications are too generic to be useful. If Anthropic fixes this upstream, the product's remaining surface disappears.
• The original riskiest assumption is untested by the evidence: nothing here shows a developer will actually keep 4+ sessions productive once visibility improves, rather than reverting to one task at a time because of review load.
• Parsing agent output for idle/prompt patterns is brittle across Claude Code versions and will break silently, which is exactly the failure mode that destroys trust in a notifier.

Questions to test first

• Build only the classifier: instrument a handful of real sessions and measure how often NEEDS YOU is correctly distinguished from DONE. If you cannot beat the noisy idle_prompt behaviour described in the issues, stop.
• Ask the subscribers on the Claude Code notification issues and the cmux classification issue to try the classifier and report false positives — cheapest available panel of confirmed sufferers.
• Install Claude Squad and Conductor and document precisely where their attention routing fails, to establish whether there is any gap left after the platform's worktree flag.
• Verify the reported `claude --worktree` flag against Anthropic's own documentation, since the evidence treats it as reported-by-source only.
• Run a diary test with five developers using the board for a week: log how many sessions they actually keep live and whether it rises, to test the parallel-throughput assumption directly.

Evidence and sources

The sources this assessment is based on. Evidence level: Indicative, counted from these sources as described in how ideas are assessed. Findings are what a source shows; anything the research only inferred is marked as an inference.

Research findings

• SupportsGitHub issue (manaflow-ai/cmux #4506) · 21 May 2026

  Shows: third-party issue tracker showing another orchestrator hitting the same status-classification problem

  An issue in the cmux multi-agent tool says its 'Claude waiting' notification is too generic — every session produces the identical title, so users cannot tell which workspace needs them — and asks for reason classification (permission request, tool approval, question, error, idle). Independent confirmation that per-agent attention routing is a real, unsolved implementation need, and that competitors ship it imperfectly.

• SupportsGitHub issue (anthropics/claude-code #36885) · 21 March 2026

  Shows: issue-tracker feature request confirming the 'agent blocks silently, no single place to see who needs you' problem

  An open issue on the official Claude Code repo states that when running multiple Claude Code sessions simultaneously there is no way to know which session is blocked waiting for user input (permission approvals, questions) and that you must manually check each tab or window; it requests native OS notifications. This is the exact core pain Flight Deck's NEEDS YOU board + desktop notification addresses, observed outside the communities where the idea originated.

• SupportsGitHub issues (anthropics/claude-code #12048 and #36850) · 20 November 2025

  Shows: issue-tracker evidence that existing notification hooks are too noisy to build a reliable 'needs you' signal

  Feature request reports the idle_prompt notification hook fires after every response, making it unusable for signalling genuine attention needs (AskUserQuestion, approval prompts); a related issue (#36850) asks for a terminal bell specifically on tool approval, distinguishing 'I'm done' from 'I need you'. Supports the problem but also flags a buildability risk: reliable RUNNING/NEEDS YOU/DONE classification is the hard part, since the upstream signal is noisy.

• Weakens the caseTechnical blog posts describing built-in Claude Code worktree support · 29 July 2026

  Shows: platform change absorbing part of the product's value

  Multiple independent write-ups report that Claude Code shipped built-in worktree support (a `claude --worktree <name>` flag creating isolated sessions on their own branch under .claude/worktrees/). If accurate, the 'creates a branch + worktree for you' half of Flight Deck is now a platform primitive, leaving only the cross-session status board and attention routing as defensible surface. Treated as reported-by-source rather than independently verified against Anthropic docs.

• Weakens the caseComparison roundups and vendor/project pages (Claude Squad GitHub, Conductor, Vibe Kanban, Crystal, Nimbalyst)

  Shows: crowded competitive field with near-identical positioning

  Claude Squad is a Go-based terminal UI that manages multiple Claude Code/Codex/Aider/OpenCode agents in isolated git worktrees (reported at ~6.8k stars); roundups also list Conductor (macOS app, worktree-per-agent with diff review and merge), Vibe Kanban, Crystal and Nimbalyst as direct equivalents. Flight Deck's described feature set — worktree per task, status board, diff + one-key merge/PR — overlaps almost completely with shipped tools.

Where the problem was reported

Public posts in which people described this problem, grouped into one problem before research began.

• Show HN: AI Harness that lets a graph of Codex and Claude intercommunicate · github.com · 29 August 2026
• Ask HN: How do you use multiple sessions for software engineering? · news.ycombinator.com · 28 August 2026
• Ask HN: How many of you juggle multiple agent sessions at the same time? · news.ycombinator.com · 27 August 2026

Looked for, not found

• Searches surfaced issue trackers, vendor pages and blog/newsletter posts (including practitioners describing losing track while switching between terminal tabs and building their own session monitors), but no job posting, freelance listing, keyword-volume dataset, or app-store/product review with a verifiable purchase signal. Willingness to pay is therefore unestablished — most alternatives found are free and open source, which is a further monetisation risk.