Skip to main content
Glama
kitepon-rgb

aiterm-mcp

codex_agent

Launch a dialogue agent in a persistent terminal for implementation, review, and research. Send prompts asynchronously and receive completion notifications via a separate process.

Instructions

【Codex (OpenAI)】の対話エージェント TUI を永続端末に起動する。実装・レビュー・調査を対話で回す。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 / reasoning_effort を引数で指定可(省略時は端末 config/CLI 既定を継承。実効値は起動応答に明示)。

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(例: gpt-5.6-sol / gpt-5.6-terra / gpt-5.6-luna)。省略時は端末 config/CLI 既定を継承(端末側のピンがそのまま効く。実効値は起動応答に明示される)
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
session_nameNoセッション名(省略で自動採番)
reasoning_effortNoreasoning effort(思考レベル)。low/medium/high/xhigh/max/ultra(CLI 版依存)。ultra は max 推論+proactive 自動委譲 ON=使用量急増注意(明示要求時のみ)。省略時は端末 config/CLI 既定。

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
schemaYes
providerYes
session_idYes
event_cursorYes
wait_commandYes
submit_residueYes
managed_completionYes
Behavior4/5

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

With no annotations, description fully discloses behavior: non-blocking launch, parent does not wait, completion notification mechanism, result retrieval via pty_read, model/reasoning_effort defaults inheritance, and usage spike caution for ultra. No contradictions.

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?

Description is lengthy but front-loaded with main purpose. Structured with usage pattern first, then parameter details. Some redundancy but necessary for clarity given tool complexity.

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?

Covers main behavior, interaction pattern, completion, parameter semantics, and result retrieval. Output schema exists, so return values not needed. Minor gaps: no mention of error handling or session lifecycle after completion beyond exit codes.

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 baseline 3. Description adds extra context: effective model shown in response, ultra reasoning usage warning, prompt sent immediately, directory context. Adds value beyond schema.

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?

Description clearly states it launches a Codex (OpenAI) dialogue agent TUI in a persistent terminal for implementation, review, and research via conversation. Distinguishes from siblings like composer_agent and claude_approval by being OpenAI-specific and TUI-based.

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?

Provides detailed when-to-use context: for interactive tasks, non-blocking dispatch, fire-and-forget, completion via separate process (aiterm-wait). Mentions not to wait, not to foreground, and how to retrieve results. Lacks explicit when-not-to-use but implies via contrast.

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/kitepon-rgb/aiterm-mcp'

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