Skip to main content
Glama

create_agent

Design a Claude Code subagent in one call: gather specialist contributions, draft, review, revise, then save the agent and skills or preview files.

Instructions

Have specialists design a new Claude Code subagent in one call: sequential contributions, architect draft, independent reviews, then revision if needed. Pass agents and task, or from_session (the id of a live collaboration or meeting, e.g. collab-4k9q2mzt, or of any ended session in the archive) to inherit participants, topic and discussion; explicit agents are combined with inherited ones. Each contributes expertise, guardrails and skills. Default write: true saves the agent to ROUNDTABLE_AGENTS_DIR and new skills to ROUNDTABLE_SKILLS_DIR; existing agents are never overwritten. write: false previews files without writes. Creation includes the destination project's .claude/skills in lookup even when the configured skills directory differs. Skill lookup follows Claude Code precedence: personal ~/.claude/skills, then .claude/skills beside the agent file when it is in .claude/agents, then ROUNDTABLE_SKILLS_DIR. Any skill found is reused, never overwritten or shadowed. Tools fail closed: a list with no allowlisted matches or a value of the wrong type is rejected and the architect retries once. Omitting tools gives the new agent tools: Read, Grep, Glob. The result reports actual paths, warnings and next delegation instructions: use Claude Code's Agent tool with the returned agent.name as subagent_type when saved in .claude/agents, or start_meeting. perform_task: true with writes starts a private meeting on the task; follow its next instructions with say and end_meeting. Public workshops post contributions, reviews and a redacted summary of the final definition (name, description, model, tools, skill names and status, contribution credits, changes and open questions), without its system prompt, skill instructions or descriptions derived from instructions; copied private passages in summary fields are withheld. They never post context, personas, fleet listings or source-session transcripts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoOptional agent name hint; normalized to a slug, with a suffix on collision.
taskNoWhat the new agent should do; required unless from_session supplies a topic.
modelNoModel id. Defaults: claude-sonnet-5-5 (anthropic), gpt-5.6-luna (openai), zai-org/GLM-5.3 (together), qwen/qwen3-235b-a22b-instruct-2507 (replicate), qwen3:14b (ollama), default (openai_compatible). Model aliases: "opus" (claude-opus-5-5), "sonnet" (claude-sonnet-5-5), "haiku" (claude-haiku-5-5). Replicate accepts owner/name, owner/name:version, or a https://replicate.com/owner/name URL.
writeNoDefault true: save agent and new skills. False: return preview files and write nothing.
agentsNoContributing personas; combined with from_session participants and deduplicated. At least one participant is required.
publicNoDefault false. Only set true when the human explicitly asks for a public session. When true, the whole session is posted live to the configured public channel and is world-readable: the topic/agenda, every agent reply, every message you send with say/nudge, and the summary. The context argument is never posted, but agents may paraphrase it in their replies, so keep context generic. Never include personal information, credentials, or private code anywhere in a public session. The result includes public.url so the human can watch live.
roundsNoContribution rounds, default 1, clamped to 1..3; reviews follow the architect draft.
contextNoOptional background for the design; never posted publicly.
base_urlNoOnly with provider "openai_compatible": base URL of an OpenAI-compatible /v1 endpoint (e.g. http://localhost:1234/v1). Overrides OPENAI_COMPATIBLE_BASE_URL. OPENAI_COMPATIBLE_API_KEY, if set, is sent only to the OPENAI_COMPATIBLE_BASE_URL origin or one listed in ROUNDTABLE_OPENAI_COMPATIBLE_TRUSTED_ORIGINS; any other base URL gets no Authorization header and must be https (http only to loopback, or to private addresses with ROUNDTABLE_ALLOW_PRIVATE_BASE_URLS=1), never a cloud metadata or (without that setting) private address.
providerNoLLM provider. Default: anthropic. Options: anthropic, openai, together, replicate, ollama (local, when reachable), openai_compatible (set OPENAI_COMPATIBLE_BASE_URL or pass base_url).
from_sessionNoId of a live collaboration or meeting (collab-…, meeting-…) or of any ended session in the archive, whose participants and discussion should shape the agent.
perform_taskNoCreate + write only: start a private meeting with the new agent on its task. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A4.1/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the minimal annotations, disclosing default write behavior, exact destination directories, the no-overwrite guarantee, skill lookup precedence, fail-closed validation with a single retry, and the default tools applied when none are given. It also documents what the result reports and the redaction rules for public sessions, which the destructiveHint/openWorldHint flags alone could never convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is dense and largely relevant, but it is delivered as one long run-on paragraph with no breaks between creation, write, skill-lookup, and public-posting concerns. The public-session redaction material is lengthy boilerplate that is only conditionally relevant, and the front-loaded purpose statement competes with a lot of trailing detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, no-output-schema, open-world mutation tool, the description covers the decisions an agent must make: create vs preview, inherit vs specify agents, and whether to chain into a meeting. The remaining gap is the referenced-but-absent tools parameter and no guidance on choosing between create_agent and improve_agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning about interactions the schema cannot express: how agents merge and deduplicate with from_session participants, that task is required unless from_session supplies a topic, and that write defaults to true. A minor flaw is that it references a 'tools' argument that does not appear in the schema, which could confuse parameter selection.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause gives a specific verb and resource ('design a new Claude Code subagent in one call') and sketches the process (architect draft, independent reviews, revision). It is clear what the tool produces, but it never names the obvious sibling alternative improve_agent, so the agent must infer that this tool is for new agents only.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives concrete routing conditions: pass agents and task, or from_session to inherit participants, and it explains that explicit agents are combined with inherited ones. It also defines write:false as a preview and perform_task:true as the follow-on path, but it never states when to prefer improve_agent or another sibling over creating a fresh agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.