start using Turborepo with your agents
sign up, open a project, and add Turborepo to its setup script in settings → server.
turborepo is what stops an agent rebuilding an entire workspace to check a one-line change. installed in each conversation's sandbox it puts turbo on the path for every agent in the project.
what agents do with it
the value is the task graph. an agent runs the repository's own pipeline, so type checking, linting, building and testing happen in the order the repo declares and only for the packages the change affects. the second run after a small edit hits the cache and finishes quickly, which is what makes an iterate-and-verify loop practical inside a single conversation. it also removes a common failure mode: an agent that invents its own build command runs the wrong steps in the wrong order and reports a green result the repository would not agree with.
the matching skill
turborepo ships with a skill of the same name. its main rule is to prefer the repo-local binary through pnpm turbo or npx turbo when the repository pins a version, so the run matches the lockfile. it also names the node.js dependency. skills load only for the agents you assign them to.
example tasks
- 01
run the checks the way ci does and fix whatever fails.
the agent runs the repo's turbo pipeline in the conversation's sandbox, reads the first real failure, fixes it, and reruns, letting the cache skip everything untouched.
bashreadedit - 02
which packages does this change actually affect?
it runs the task graph and reports the packages that rebuilt rather than the ones it guessed would, so the review scope comes from the tool and not from memory.
bashgrep
what to know before installing
the project needs a sandbox, and node.js must come earlier in the setup script. pnpm is the usual companion, since most turborepo workspaces are pnpm workspaces.
how to install Turborepo
Turborepo goes in the project's setup script, not once per team and not on your laptop.
- give the project a sandbox
Turborepo runs in each conversation's sandbox, on your team's own sandbox provider account. an owner or admin connects a provider once on the team's providers page, then picks it and a default size for the project, at creation or later in settings → server. a project with no sandbox has nowhere to run it.
- add it to the setup script
settings → server holds the project's setup script, a bash script that runs once on each new sandbox, in /project, with sudo. add Turborepo's install commands there and save.
- the next sandbox runs it
the script runs when a conversation's sandbox is created or reused, on the conversation's first turn. settings shows the last run with its exit code and output, and a failed run leaves the sandbox usable rather than blocking the project.
- agents use it through bash
from then on every agent in the project reaches Turborepo with the bash tool, on the same filesystem as the checkout they are working in. the conversation's sandbox keeps it between turns, sleeping when idle and waking with the next one.
where Turborepo actually lives
each conversation in a project gets its own sandbox on your team's sandbox provider account, and the project's setup script in settings → server decides what is on it. two projects never share a filesystem, so a version pinned for one client cannot collide with another's.
the sandbox provider bills its machine time to your team's account while it runs, and aldena adds nothing. the sizes are on isolated projects, and what agents may run in the sandbox is governed by the project's tool permissions.
faq
what does installing turborepo on a project give the agents?
the turbo task runner in each conversation's sandbox. agents run the repository's own pipeline rather than inventing build commands, and turbo's cache means a second run after a small change finishes in a fraction of the time of the first.
should agents use the global turbo or the repo's own?
the repo's own. the shipped turborepo skill tells agents to prefer the repo-local binary through pnpm turbo or npx turbo when the repository pins a version, so the run matches the lockfile rather than whatever the global install happens to be.
does turborepo need anything installed first?
yes, node.js. it installs through npm, so node.js has to come earlier in the project's setup script. pnpm is usually wanted alongside it, since most turborepo workspaces are pnpm workspaces.
why does the cache matter in a project?
because a task graph that skips unchanged packages turns a five minute verification into a ten second one, which shows up directly on how quickly an agent can iterate.
spin up your first project.
one project per client, product, or piece of work, staffed with intake, requirements, build and code review agents.
