Skip to main content
Glama
quolu
by quolu

grok_agent

Launch an interactive AI coding agent in a persistent terminal for asynchronous prompt execution, reusing your CLI environment, MCP tools, and plugins.

Instructions

【Grok Build の Grok モデル (既定 grok-4.5)】の対話エージェント TUI を永続端末に起動する。通常CLIと同じHOME・cwd・project/user/local設定・MCP・plugin・skill・permission/trustを共有する。aitermは完了相関stateだけをlaunch単位で所有する。起動されたagentにはsub-agent自己認識、親session、delegation depth/lineage、delegation_allowed=trueを注入し、必要な追加委譲は許可する。turn は pty_send で送る(自動で非ブロック dispatch になる)。起動して投げたら投げっぱなしでよい=親はここで待たない。完了通知は起動応答の wait_command(初回prompt時)または pty_send dispatch 後の aiterm-wait --session --cursor を親のターンを塞がない別プロセスとして起動して受ける(exit 0=done / 3=timeout(既定600秒・未完了) / 4=closed。receiptのoutcomeが正で、done以外は未完了。ポーリング不要・foreground実行はしない)。結果回収は pty_read(agent_transcript:true)。model を引数で指定可。reasoning_effort は対話 TUI 非対応(指定はエラー)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNo作業ディレクトリ(対象リポのルート等・任意)
modelNo起動モデル。省略時は grok-4.5
promptNo起動時に渡す初手プロンプト(任意)。送信後は待たずに即返る
write_scopeNo能力宣言。read-only、または書込みを許可するパスの説明文字列。Codexのread-onlyだけはCLI sandboxで実効禁止する
session_nameNoセッション名(省略で自動採番)
reasoning_effortNo指定不可(grok CLI の --effort は headless 専用で、対話 TUI では警告の上無視される。composer は effort 自体非対応)。指定すると起動前にエラーを返す
throughline_source_sessionNo同一端末のThroughline sessionから所有権を変えずに記憶を読み、promptのmissionより前へ注入する

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
schemaYes
providerYes
session_idYes
write_scopeNo
event_cursorYes
wait_commandYes
submit_residueYes
managed_completionYes後方互換field。trueはaiterm完了相関が有効という意味で、project/user環境の隔離を意味しない
write_scope_enforcementNo
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses shared HOME/cwd/settings/MCP/plugins/skills/permissions, aiterm state ownership, injected sub-agent awareness, delegation_allowed=true, non-blocking turn dispatch, completion exit codes, timeout semantics, and the reasoning_effort error. No annotation contradiction exists.

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

Conciseness4/5

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

The description is one dense paragraph but front-loads the core purpose and then packs essential lifecycle details without filler. Every sentence conveys necessary information, though bullet points or structured separation would improve readability.

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

Completeness5/5

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

For a complex asynchronous agent-launching tool with no annotations, the description is remarkably complete: launch semantics, state sharing, delegation injection, turn sending, completion/wait mechanisms, exit codes, timeout, result collection, model selection, and unsupported reasoning_effort are all covered. The output schema handles structured return details.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline is 3. The description reinforces the model default and the reasoning_effort error, but adds little beyond what the schema already documents for cwd, session_name, write_scope, or throughline_source_session. It does not materially enrich parameter meaning.

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

Purpose5/5

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

The description clearly states that the tool launches a Grok Build dialogue-agent TUI on a persistent terminal, names the default model (grok-4.5), and describes the resource/action explicitly. It differentiates from sibling agent launchers by identifying the specific Grok model and its environment-sharing behavior.

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 strong operational guidance: the parent should not wait, completion should be monitored via wait_command or aiterm-wait in a separate process, polling/foreground execution are discouraged, and result retrieval uses pty_read. It does not explicitly name alternatives like claude_agent or codex_agent, but the context is clear.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/quolu/aiterm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server