Projects and chats

The list of projects and sessions is assembled from Claude Code's transcripts. An open session is loaded page by page — the files can be tens of megabytes, and nobody reads them whole.

Projects follow working directories

A project in Clauder is not a folder inside ~/.claude but a working directory. A session started in /var/www that went on to work in /var/www/sw3 is visible in both projects: every cwd in the transcript is reduced to the repository root.

That gives a pleasant side effect: one and the same folder worked in from both sides of WSL and Windows shows up as a single entry with a shared chat list.

The session feed

Two modes. The collapsed one mirrors the CLI console: one line per event (⏺ Read(…/types.ts) → ⎿ 42 lines), a click opens the details. The debug one (switched on in the settings) shows everything, including service records and the innards of calls.

Quiet mode (a switch under "⋮" in the chat) hides everything that isn't conversation behind one line: what is left of the agent are messages and questions, while thinking, reads, commands and their output fold into "⋯ 9 actions · 5 thoughts". A tap unfolds the batch in place, nothing is lost — and a reply dozens of lines long stops drowning the conversation.

A time on every action and day separators — "Today", "Yesterday", "1 August", as in messengers. You can see when a call ran and how long it took.

The model's thinking is visible in Clauder's own chats too: the SDK is asked for a summary, so "💭 thinking" doesn't unfold into emptiness.

The agent's plan (TodoWrite, TaskCreate/TaskUpdate) is drawn as a checklist and pinned to the header as "☑ Plan · 2 of 7".

A loaded skill becomes a card. After a Skill call the instructions from SKILL.md arrive as a separate record and, unfolded, take up half the feed: so it is a "🧩 skill · <name>" line with the body behind a toggle.

Live command output. While Bash runs, what the command is printing right now is visible under the call's arguments; a background task gets a full-height screen of its own for that.

Subagents

The CLI writes a subagent's work into separate files next to the transcript. A record with a Task call gets a "⤷ type · N records" link that opens the subagent's feed as its own screen.

Your own titles, favourites, order

A title from the transcript isn't always telling — a chat and a project can be renamed, starred to the top of the list or hidden.

A chat's name is shared with Claude Code: one renamed in the CLI reads the same in the clients, and a rename from Clauder goes into the transcript as an Agent SDK record and is visible in the terminal.

You can rename right from a list. A pencil sits next to a chat in the project's chat list, in "recent sessions" in the sidebar and on the agents screen, and on the cards of working agents: the name is edited in place. On Android — with the pencil or a long press.

"New chat in this project" is on every chat — in "recent sessions", in the sidebar's chat tree, on the cards of the project's chat list and of working agents. The new chat opens in the directory of the session you pressed it on, so there's no need to pick the folder again. In the web UI and on Android.

The chat list is sorted by the last message or by the last time you looked — like recent documents. A live session's transcript grows every couple of seconds and reshuffles the list under your hands, so the second order is sometimes more comfortable.

Read and unread. A session that grew while you weren't looking is highlighted and labelled. The mark lives on the server: what was read on the phone doesn't glow in the browser.

Deleting a chat or a project

Hiding means putting out of sight: the file stays, and both claude --resume and the terminal see it. Deleting means removing for good, and there is nothing to restore it from afterwards.

A chat. Every chat has a bin, not only hidden ones. Deletion is confirmed by a second tap on the same button ("sure?" fades after five seconds). If the chat is replying right now, the reply is stopped first — otherwise the CLI would write the deleted transcript back. Everything Clauder remembers about the chat goes with it: message bookmarks, share links, auto-continue, the queue, spend, the title. A read-only key doesn't see the bin.

A project. "Delete project" is in the project card and in the app's project panel. It asks twice: first a dialog with what will go and what will stay, then "Sure? N chats will be deleted for good". All of the project's chats go (including ones run from the other side of WSL and Windows) along with all its marks in Clauder. The project's own files on disk are not touched — only its directory in ~/.claude/projects is removed.

Claude's memory of the project — what the agent kept between chats — stays by default: a new chat in the same folder picks it up. To erase it as well, tick "Also erase Claude’s memory of this project".

Only the owner can delete a project: a project is shared by all keys. Works in the web UI, the app, VS Code, on the iPhone and on Android.

Search

Search covers chat titles and the text of the conversation — across every project and source at once. The result card shows where the match was.

How updates arrive

Two ways at once: a file watcher and polling of the file's tail (1.5 s during an active reply, otherwise 5 s). The polling is deliberately not switchable — watcher events get lost on network mounts, and without it an open feed would sometimes simply freeze.

What next

• Chat with the agent — how to continue a session and run a new one.
• Who's working now — the screen of live chats, subagents and background tasks.
• Spend and limits — how much has been spent and what is left of the plan.