Tools
Built-in tools the LLM can call when working in OpenCorvus.
OpenCorvus ships a set of built-in tools the agent can call. Tools live under packages/opencorvus/src/tool/ and are registered through packages/opencorvus/src/tool/registry.ts.
Built-in tools
| Tool | Purpose |
|---|---|
bash | Execute shell commands through the configured shell |
browser_preview | Inspect and interact with a browser preview |
read | Read a file (line-numbered, range-aware) |
write | Create or overwrite a file |
edit | Apply targeted string replacements |
apply_patch | Apply a unified diff |
glob | Find files by glob pattern |
search_code | Search file contents |
list | Directory listing |
webfetch | Fetch URL contents |
websearch | Run a web search |
memory | Persistent memory store |
todoread / todowrite | Read and update the agent’s todo list |
external_code_search | Search external code sources |
skill | Load a projected Skill |
delegate_agent | Dispatch a bounded helper from coding or chat assistants |
panel | Operate the OpenCorvus control panel |
planner | Manage the assistant planning surface |
mission_state | Read Mission coordination state |
wait | Yield until an external wake condition |
request_orchestrator_decision / send_mailbox_message | Exchange visible worker coordination messages |
question | Ask the user (when OPENCORVUS_ENABLE_QUESTION_TOOL=1) |
schedule | Schedule follow-up actions |
batch | Run a batch of tools in one turn |
analytics | Emit telemetry events |
Task Orchestrator tools
Task Orchestrator sessions receive scheduler tools from the active expert-squad projection. These are not global ToolRegistry entries:
dispatch_agentdispatches one exact dynamic agent ID declared under the activecapability_projection.agentsmap.manage_taskowns Task lifecycle and creates or revises Delivery Slice contracts. It does not complete/reject/retry a Goal or bind Goal workspaces.
Disabling a tool
{ "tools": { "write": false, "bash": false, },}This prevents the LLM from receiving the tool definition. Use it for review-only or sandboxed agents.
Permissions
Most write/execute tools route through the permission system. See Permissions for allow / ask / deny rules.
Adding new tools
Additional executable tools belong to an installed expert-squad package. Its manifest projects exact package tool references only to the active scheduler or dynamic agents that declare them. Plugins may intercept tool definitions and execution, but cannot register agent tools.