Commands
Run lucitra with no arguments to open the shell, or lucitra <command> to run one and exit.
The same commands are served to other agents by lucitra mcp, and every one of them is checked
the same way wherever it comes from.
Reads
Change nothing. Safe from any surface, including a read-only bridge.
| Command | Arguments | What it does |
|---|---|---|
plan | goal | Scope a goal into tasks without running any of them |
chat | message | Ask your chief of staff something, in this repo’s conversation |
ask | question | Search the project brain, falling back to the chief of staff |
survey | What Agent Teams can work out about this repo without being told | |
candidates | Work this repo already says needs doing: issues, drafts, old TODOs | |
route | goal | Ask the chief of staff who should take a request. Starts nothing |
repos | The repositories a request may start in, this session’s first | |
tasks | What has run and what is running, newest first | |
dashboard | Where the work stands across every repository, and what the week cost | |
threads | where | Every thread in this repo: what ran, what needs you. everywhere for all |
search | text | Find a line across every conversation in this repo |
models | Which model each agent runs, and on which runtime | |
mcp | Which MCP servers each agent may reach | |
agents | The roster, and what each agent is configured to do | |
company | The team this repository declares, and who reports to whom | |
org-chart | Every org chart on this install, and which one delegation is checked against | |
validate-team | path | Read an agent team from a folder and list what is wrong with it |
integration-health | refresh | Whether each integration and key source works, and the fix when not |
schedules | Every schedule the agent teams declare, whether it is on, and what it last did | |
brain-loose-links | Links from the brain files that are not pages: the index, the log | |
trigger-preview | schedule | What each trigger would fire on now, without firing: [<team>/<project>/<task>] |
identity | company | Who a company’s chief of staff is here: its name, photo and look |
identities | Every agent’s name and photo on this install | |
budgets | Every token budget, and what each team or agent has spent this period | |
trading-limits | Trading limits every order is held to: defaults, yours, each team’s | |
secret-sources | Where integration secrets are read from: GCP projects and env files, in order | |
model-providers | Where models can come from besides local: your own keys for a provider | |
run-events | run | One run, step by step: every tool call, its output and what the agent said |
connectors | refresh | MCP servers your runtimes connect to themselves: claude.ai and config |
integrations | Which integrations the agents name, and whether Agent Teams has them | |
brain-pages | Every page in the brain: its frontmatter and what it links to | |
brain-page | path | One page of the brain, text and all: brain-page <path> |
brain-history | path | Every commit that touched the brain: brain-history [path] for one page |
approvals | Whether runs ask before anything leaves this machine, or act on their own | |
brains | Brains registered on this machine, and which one brain reads use | |
browser-host | Whether the Companion’s native messaging host is registered here | |
first-run | The queues and the places first run offers | |
preview-company | queue, place | The team a queue and a place would produce: preview-company <queue> <place> |
channels | Where Agent Teams may reach you when you are not at the terminal | |
account | Who this install belongs to, and what proves it |
Writes
Change something on this machine. A bridge refuses these unless it was started with --allow-writes.
| Command | Arguments | What it does |
|---|---|---|
seed | keep | Write what the survey found into this repo’s brain, as one page |
start-build | goal, agent, repo, team, note, push | Start a task in its own worktree, as the Builder or a named agent |
reply | thread, message | Reply in a thread; the agent that last ran there picks it up |
decline | task | Refuse a waiting push. The worktree is left alone |
teams | team | The agent teams on this install; with a slug, switch to one |
schedule | schedule, onOff | Turn one schedule on or off: schedule <team>/<project>/<task> on|off |
cancel (destructive) | task | Stop a running task’s agent. Its worktree is left as it is |
edit-agent | agent, field, value | Change a team agent’s name, title, skills or instructions |
set-identity | agent, field, value | Give an agent a nickname or photo: <team> for its chief, or <team>/<role> |
clear-identity | agent, field | Put an agent back to its role name, or its default look |
set-company-name | name | Rename your default company. A team takes its name from its package |
run-schedule | schedule | Run one schedule now, whether or not it is on: <team>/<project>/<task> |
budget | team, tokens, period, agent | Set or clear a token budget: <team> <tokens|off> [day|week|month] [agent] |
integration-add | integration, environment | Install an integration, so agents granted its tools can call them |
trading-limit | integration, key, value | Change a trading limit: <alpaca> <key> <value|default|none> |
trading-limit-tighten | integration, key, value | Tighten a trading limit; refuses a change that loosens it |
secret-source-add | `keychain | 1password |
model-provider-set | provider, setting, value | Set one model provider setting: <provider> <SETTING> <value|none> |
secret-source-remove | `keychain | 1password |
integration-remove | integration | Remove an integration; its tools leave every agent from the next run |
approval-mode | `ask | auto` |
brain-add | path, name | Register a folder kept as a brain: brain-add <path> [name] |
brain-use | name | Read from a registered brain, or repo for this repository’s own |
brain-remove | name | Forget a registered brain. Its folder is left as it is |
declare-company | queue, place | Write the team a queue and a place would produce to .lucitra/company.md |
model-preset | `claude | without-claude` |
configure | agent, setting, value | Change one setting on one agent: configure <agent> <setting> <value> |
reset | agent, setting | Put one setting back to its default: reset <agent> <setting> |
runtimes | runtime | What runtimes are installed; with an argument, switch to one |
verify-channel | channel, code | Prove a channel by echoing back the code it was sent |
revoke-channel (destructive) | channel | Stop sending to a channel. That it existed is kept |
verify-claim | claim, code | Echo back the code an identity was sent |
revoke-claim (destructive) | claim | Stop an identity proving this account. That it did is kept |
new-conversation | title | Begin a new conversation, optionally named |
conversations | conversation | List conversations; with a number, reopen that one |
Leaves the machine
Sends something outward: a push, a message, a verification code. Never run unattended without meaning to.
| Command | Arguments | What it does |
|---|---|---|
approve | task, approved | Let a waiting task push. Omit the task when only one is waiting |
team-add | source | Register an agent team from a folder, or clone one from github:owner/repo |
team-update | team | Pull the latest of a team's folder, fast-forward only, and refresh its roster |
add-channel | kind, address, label | Add somewhere to reach you: add-channel <ntfy|sms|whatsapp> [address] [label] |
claim | kind, value | Prove an identity for this account: claim <phone|email> <value> |
83 commands: 42 read, 35 write, 6 leave the machine.