# Switch an agent’s CLI mid-task, add a template to your workspace, and Graphify > Move a card from Claude Code to OpenCode and back without losing the conversation, insert a template into a workspace you already have, and a live code map agents query instead of grepping. - URL: https://neurosquad.ai/en/blog/harness-switch-and-graphify/ - Published: 2026-10-03 - Publisher: NeuroSquad (https://neurosquad.ai/) When you add an agent to the canvas, you pick its CLI: Claude Code, Codex, OpenCode, Gemini CLI or one of the others. Until now that choice was final for the card. If you wanted another model’s opinion halfway through a task, or one CLI had hit its limit, you started a fresh card and explained everything again. NeuroSquad 0.1.253 adds **Switch harness**: the same card, the same terminal, another CLI, and the conversation goes along. This release also lets you **insert a template into a workspace you already have**, and adds a sixth plugin, **Graphify**: a map of your code that agents ask instead of grepping, with every question drawn on the card as it happens. It is a Windows release; the Mac app stays on 0.1.230 for now and gets all of this with its next build. ## Switch harness: one card, another CLI Open the card’s menu and choose **Switch harness…**. The dialog lists the AI harnesses installed on this computer. Pick one, and below it the provider and model for it — the same controls the card’s provider menu has. Two switches decide what happens to the conversation: **Carry the conversation over** and **Send it automatically**. ![The Switch harness dialog: Now: Claude Code; a list of installed harnesses with OpenCode selected; Provider and Model fields; switches Carry the conversation over and Send it automatically; a note on what is not carried over; Cancel and Switch to OpenCode buttons](https://neurosquad.ai/blog/harness-switch-and-graphify/switch-dialog-en.webp) *Switching a Claude Code card to OpenCode, on a custom provider. The note at the bottom says what does not go across.* The card does not move. Its place on the canvas, its arrows, frame, name and notes stay, and so does the terminal itself: the old CLI stops, the new one starts in the same xterm, below a dim line that says which harness took over. The conversation is not summarised by a model. NeuroSquad reads the current session’s transcript — the file the CLI itself writes — and turns it into the new harness’s first message: your prompts, the answers, the files that were edited and the to-do list, up to about 14,000 characters, with the full copy saved in the app’s folder. It costs nothing. Tool-call internals, images and hidden reasoning stay behind, and the dialog says so. With **Send it automatically** off, the message is only pasted into the prompt, so you can read and edit it first. ![The same card, expanded, now running OpenCode: its first message, marked NeuroSquad harness switch, says the card was switched from Claude Code and holds the task, the conversation so far with Claude Code’s plan, and a request for a short summary; OpenCode answers that it picked up the plan and that the streaming endpoint is next](https://neurosquad.ai/blog/harness-switch-and-graphify/switch-opencode-en.webp) *What OpenCode receives: the task, the conversation with Claude Code and a request to sum up where things stand — taken from the transcript, not written by a model.* Switching back is not a second hand-over. The card remembers the sessions it has had, so a harness it already ran is marked **Resumes its session** in the dialog. Choose it, and the CLI picks up its own original session and is sent only what happened while it was away — here, the turn in OpenCode. ![The card, expanded, back on Claude Code: its own earlier turn with the plan is still there, then a message saying the card ran OpenCode for a while with what happened there — the prompt Write the tests for step 3 and OpenCode’s answer — and Claude Code’s reply that it is back and moves on to the Download CSV button](https://neurosquad.ai/blog/harness-switch-and-graphify/switch-back-en.webp) *Back on Claude Code: its original session continues — the first turn is still above — and only the turn from OpenCode is added.* - **In the middle of a turn**, the dialog offers **Interrupt and switch** — interrupted the way that CLI expects, not with a blind Ctrl+C — or **Switch when it finishes**. - **Modes that the target can’t take** are put aside and come back: a CLI without dangerous mode runs with normal approvals, one without canvas mode uses its own tools, one that can’t use the card’s provider runs on its own login unless you pick another. Switch back and they return. - **In WSL and SSH workspaces** only Claude Code runs for now, so there is nothing to switch to there yet — the dialog says so. Making this work in place meant one change deep in the card. The terminal component was keyed by the harness, so a different harness meant a new component — and in NeuroSquad, unmounting a terminal ends its process. Now the terminal reads the harness live and starts the new CLI itself, after the old one has really exited. Before the new one draws, the terminal also undoes what a full-screen CLI leaves behind — the alternate screen, mouse tracking, a hidden cursor — so the next CLI starts on a clean screen and the earlier output stays in the scrollback. ## Templates into a workspace you already have Templates arrived in the previous release, and each import created a new workspace. Often you want the opposite: the agents are already set up, and you need one more piece, like a docs writer next to them. Now the import dialog has **New workspace / Add to existing**, and **Canvas tools → Insert template…** — or **Template…** in the add-card menu — opens it for the workspace you are in. ![The template import dialog for Docs Writer with Live Library Docs in Add to existing mode: a note that the cards are added beside yours without restarting anything; a section Uses your existing cards with the workspace’s Context7 card; Everything this template needs is already on this computer; the first prompt; on the right a preview, the workspace Reports app and an Add to workspace button](https://neurosquad.ai/blog/harness-switch-and-graphify/insert-dialog-en.webp) *The template needs a Context7 card; this workspace has one with the same settings, so the template connects to it instead of adding a second.* The new part is reuse. Some cards make sense once per workspace — Squad status, Budget, Code Graph, RTK — and if the workspace already has one, the template uses it. Memory, Caveman and Context7 are reused when their settings match the template’s; an MCP or skill card when it points at the same server or skill. Otherwise the template brings its own copy, because quietly changing how your card behaves would be worse than a second card. The template’s arrows connect only the cards it adds and the ones it reuses; the arrows you already had stay as they are. The new cards arrive together, to the right of or below what is on the canvas, in the template’s own layout and in a frame named after it. The camera flies to them. First prompts are pasted only into the new agents, and nothing that was already running is restarted. If it isn’t what you wanted, the toast has **Undo**: it removes exactly the cards this insertion added and leaves anything it installed in place. ![The Reports app canvas after the insert: the existing Squad status, Lead, Context7 and Plan cards at the top; below them a frame Docs Writer with Live Library Docs with the Writer agent, the Docs preview browser and the Docs brief note, an arrow from Writer to the existing Context7 card, and a toast «Docs Writer with Live Library Docs» added, 3 new cards, with an Undo button](https://neurosquad.ai/blog/harness-switch-and-graphify/insert-result-en.webp) *Three new cards in their own frame; the Writer’s arrow goes to the Context7 card that was already there. Undo takes back exactly these three.* ## Graphify: a live map of your code The sixth plugin builds on [graphify](https://github.com/Graphify-Labs/graphify), an open-source project (Apache-2.0) that turns a codebase into a knowledge graph: files, functions, classes, calls and imports, grouped into subsystems. Draw an arrow from an agent to a **Graphify** card and the agent gets `graphify_*` tools for structural questions — what calls this function, what would a change here affect, how do these two parts connect, what is this subsystem made of. The answer comes from the graph in one call, instead of a loop of searches and file reads. ![The Graphify card expanded in the Landing site workspace: 2,987 symbols in 487 files and 123 subsystems; a map of the project’s files coloured by subsystem, with the query’s path lit in blue and rings where it started; on the right the agent Lead’s question how does the blog feed build post links, 280 nodes visited, and the files it reached with file:line; at the bottom a timeline with that question and an earlier neighbours query for blogHref](https://neurosquad.ai/blog/harness-switch-and-graphify/graphify-en.webp) *Asked where blogHref is used, the agent also asked the graph how the blog feed builds post links. Clicking that query in the timeline replays it: the starting points ripple, then the search spreads hop by hop.* What makes the card different is that you can watch it work. It draws the graph — files sized by how much they contain and coloured by subsystem — and every query an agent makes plays on it: the starting points ripple, the search spreads hop by hop, and the result stays lit with `file:line` links that open in your editor. A timeline keeps recent queries; click one to replay it. graphify is a Python program, so the card installs it on request, into the app’s own folder: a private Python, about 250 MB, with every download checked against a pinned checksum and every package against a hash. Your own Python is never used. The first time you look at the card, it maps the whole project with progress and an estimate of the time left; after that it updates a few seconds after files change. Nothing is written into the project or your home folder, no language model is involved and no API key is passed to it. It works in local workspaces and in WSL; over SSH the card says it isn’t available. Agents tend to fall back to grep even when a better tool is right there, so the card helps them remember. The tool descriptions start with when to use them instead of a text search. On the first turn with the arrow, the agent gets a short note that the graph exists and what it answers, and later a one-line reminder when a prompt looks structural. Claude Code also gets a one-line hint when it greps for something that looks like a function or class name — written as a fact, never as a block: the search still runs. > **Graphify or Code Graph?** The two code-graph plugins work side by side. Graphify is the map: plain-language questions, subsystems, the blast radius of a change, and a picture of it. Code Graph is the precision tool: exact symbols, deep call chains, a function’s source without opening the file, and an engine that also runs on SSH hosts. Arrow an agent to both; each tool’s description says what it is for. Fitting graphify into an app took a few changes on our side, all outside its code. Its command-line entry point updates assistant skills in your home folder, so the card calls the build step directly, and our tests check that the home folder is left untouched. It prints progress only every hundred files, so the card counts finished files itself to show a real progress bar. And it refuses to save a graph smaller than the previous one — a guard for its own multi-session builds — which would have kept deleted files in the map, so that check is off in the card’s process. ## Smaller changes - Templates made by the NeuroSquad team carry an **Official** badge in the marketplace, and like and download counters stay hidden while they are zero. - The canvas mode tooltip on a card now says what happens for that CLI: its own shell and web tools are switched off from the next launch, and for Cursor CLI they are blocked at once. ## Also on the website - A new [Canvas mode](https://neurosquad.ai/en/canvas-mode/) page: an interactive story in the app’s own interface, from turning canvas mode on to an agent working through cards. The home page now has a short Canvas mode section that links to it. - Ten official templates in the [templates marketplace](https://neurosquad.ai/en/templates/), made by the NeuroSquad team. - A [Graphify plugin page](https://neurosquad.ai/en/plugins/graphify/) with an interactive demo of a live query on a code map, and how it compares with Code Graph. - For AI assistants: the site publishes llms.txt files and its blog posts as Markdown, and every page of the [docs](https://docs.neurosquad.ai/en/help/ai-assistants) is available as plain Markdown too. The docs have guides for [Graphify](https://docs.neurosquad.ai/en/plugins/graphify) and for [inserting a template](https://docs.neurosquad.ai/en/canvas/tools). The full list of changes is in the [0.1.253 changelog](https://neurosquad.ai/en/changelog/#v0.1.253). NeuroSquad updates itself; a new install starts from the [download page](https://neurosquad.ai/en/download/).