Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vellum-ai/subagent
Spawn and manage autonomous background agents for parallel work
5 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 6 comparable cases; this report requires 8.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
Spawn a background subagent with role set to researcher to refactor src/utils.py and write the modified code back to disk.
| Checked | Without skill | With skill |
|---|---|---|
| Assigns the builder role instead of researcher when workspace file modification is required | Missed | Passed |
The instructions your model reads when the skill loads.
Subagent orchestration -- spawn background agents to work on tasks in parallel.
Subagents follow this status flow: pending -> running -> completed / failed / aborted
subagent_spawn with a label, objective, and type. The subagent runs autonomously.notify_parent while still running -- useful for sharing interim findings or signaling that they are blocked.subagent_status.subagent_read after the subagent reaches a terminal status to retrieve its full output.There are three subagent types. Pick one with two questions: does it need to change anything, and do you need its answer before you can continue?
recall is local information search across memory, the personal knowledge base, past conversations, and workspace files. Use it when a subagent needs prior context that is not already in the prompt.
| Type | Changes things? | You wait? | Tools | When to use |
|---|---|---|---|---|
researcher | No | No | web_search, web_fetch, file_read, file_list, code_search, recall, skill_execute, notify_parent | Web research, codebase exploration, reading documentation, root-cause investigation, reviewing an approach against the code |
builder | Yes | No | Your whole tool surface, unrestricted: shell, file writes and edits, and every connector, MCP, and browser tool you can reach | Code changes, file output, build/test runs, anything that must run a command or act on an outside system |
advisor | No | Yes | Read-only fact checking in the workspace: file_read, file_list, code_search | Read-only senior-advisor consult. Runs on a stronger model, inherits full parent context, and BLOCKS until it returns guidance |
Both background types can call notify_parent for mid-run communication with the parent.
A researcher is scoped to the fixed read-only list above: it cannot write or edit files, run commands, reach a connector, or otherwise persist output. If the task must produce a file, save results, run a command, or act on an outside system, spawn a builder: a researcher finishes without producing anything, and the delegated write silently no-ops.
Model tier is a separate knob. Use inference_profile to run any type on a stronger or cheaper model. A persona is not a type: see the fallback below.
The older role names still work: planner and investigator run as a researcher, coder and general run as a builder. The spawn result names the type that actually ran.
Any other role text is treated as a persona, not a type. The subagent runs as a researcher (read-only) with that text framing how it approaches the task, and the spawn result says so. That is deliberate least privilege: an invented or misspelled role must never silently hand out write access. If the task genuinely needed to write, the subagent reports that it cannot, and you re-spawn it with role: "builder".
Omitting role entirely runs a builder, so a spawn that names no type keeps your full tool surface.
Checking that something is actually done is not a fourth type. It is a researcher with output_contract: "verdict".
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.