aiterm-mcp: Instructions file for Codex

AGENTS.md

aiterm-mcp AGENTS.md is an instructions file for Codex, OpenCode from kitepon/aiterm-mcp. It costs 3,895 tokens per session, scanned A, original, MIT.

Project instructions for aiterm-mcp, a tool that develops and runs Aiterm, including its terminal sessions, agent launches, configuration, diagnostics, and recovery rules. They define which parts of the product this repository owns.

In plain words
What is it for?
Use them when changing Aiterm installation, sessions, schemas, migrations, launchers, diagnostics, release documentation, or platform-specific behavior.
Why use it?
They prevent changes that break the project’s public contracts, platform support, or separation between the launcher and the agent harness.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is kitepon/aiterm-mcp's own configuration. It tells Codex and OpenCode how to work on aiterm-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aiterm-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kitepon/aiterm-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kitepon/aiterm-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kitepon/aiterm-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aiterm-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kitepon/aiterm-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/kitepon/aiterm-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kitepon/aiterm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kitepon/aiterm-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aiterm-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kitepon/aiterm-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kitepon/aiterm-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,895 This file is loaded in full into every session.
When invoked 3,895 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.03895 $0.03895
Opus 5.5 $0.01558 $0.01558
Sonnet 5.5 $0.00779 $0.00779
Haiku 4.5 $0.00390 $0.00390

Measured 3d ago against content hash a1b09705dd61, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aiterm-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

aiterm-mcpで働くAIのプロジェクト正典。利用者向け公開契約はREADME/ 日本語README、設計はDESIGN、文書地図は docs overview、公開工程はRELEASEを正とする。 版別の変更と完了証拠はCHANGELOG、docs/adr/、docs/archive/に置き、 このファイルへrelease日誌を複製しない。

製品と所有境界

本repositoryはAitermを単独で開発・導入・運用・診断・復旧・更新・releaseできる状態を所有する。 install、設定、PTY/session、agent相関state、schema、migration、diagnostics、recovery、公開物の正本は このrepository内に置く。dotagentsは任意の工場統合、host wire、製品間compatibilityと統合受入を担うが、 Aitermの製品判断・実行・releaseを制御せず、通常利用の必須依存でもない。

現行契約

  • 導入後の正規入口はaiterm-setup。依存準備、MCP端末の実行、検出したAIのユーザー登録と読戻しを所有する。 npm lifecycleからは設定を変更せず、外部工場の設定補完を前提にしない。
  • Node.js 18以上。POSIXはtmux、Windows nativeはpsmux 3.3.8以上+Git for Windowsを使う。 Windowsの対話shellはPowerShell 7だけとし、Windows PowerShell 5.1、PowerShell 6、cmd.exe、 WSL bridgeへfallbackしない。
  • 公開面は19 tools。PTY 7、標準agent_launch 1、deprecated互換launcher 3、agent_models、 agent_configure、agent_goal、agent_auth、agent_approval、claude_turn、claude_approval、diagnosticsである。
  • pty_listは明示した非秘密envキーだけを照会し、pty_observeはpaneとharnessの生存・native PID・ 状態・活動を区別する。取得不能はnull/unknownで返し、生argvと画面本文を観測receiptへ出さない。
  • trust_project:trueのlaunchはpromptなしでも既知の起動準備とharness生存を確認する。 初手の未送信・送信済み未確認・開始確認を区別し、終了したharnessの残画面へ送信しない。
  • agent_launchはharnessとmodelを別軸にする。harnessはagent loop、認証、hook、session、 transcriptを所有し、modelはそのharness上で選ぶ。ComposerはCursorのmodelの一つで、harnessでもGrokのmodelでもない(cursor-cli + composer-2.5-fast)。
  • launcherは直接CLIと同じ通常HOME、project/user設定、MCP、plugin、skill、permission、trust、 memory、historyを使う。Aitermはlaunch相関、完了event、bounded result、cleanup metadataだけを所有し、 credential/設定をcopy、snapshot、filterしない。
  • agentへの送信は非ブロックdispatchで即返す。Codex親は公式queueへ配送し、macOS・WindowsのSteer選択時は公式の同期hookで 同じターンへ取り込み、終了後は公式queueで再開する。Claude Code親は公式asyncRewake hookで 回答本文を自動配送し、親はwaiterと回答回収を呼ばない。Cursor親は公式hookのadditional_contextで 次のツール返りへ本文を差し込み、idle時はreceiptのwait_process(cursor-parent-receive)の終了で起きる。 それ以外の親はreceiptのwait_processを別processとして起動し、 outcomeを判定してpty_read(agent_transcript:true)またはclaude_turn recoverで回収する。 親自身のturnをforeground waiterで止めず、timeout後にpromptを再送しない。
  • 公開復旧はpty_listで対象を確認し、該当sessionをpty_closeして同じIDで作り直す。 公開toolに全session一括停止はない。core.killAll()は内部test cleanupであり、利用者へ案内しない。
  • runtime error storeは製品所有のlocal stateで、既定ではnetwork I/Oを持たない。工場reporter configによる収集は 明示opt-inの任意adapterであり、未設定でもPTY/agent/diagnosticsは単独で動く。prompt、transcript、 path、credential、生stack/stderrを保存・公開しない。
  • BugHubへの報告は、利用者がaiterm-runtime-errors reporting enableで明示して有効にし、かつ合鍵のファイルがある端末だけが行う。 宛先は合鍵のファイルから読み、Aitermの中に書かない。送るのは別processで、MCP processは通信しない。定期的な見張りは置かず、 試験(node:testの子)からは送らない。受け取り済みにするのは、応答の署名まで確かめた時だけ(ADR 0079)。
  • 実行時エラーとして記録するのは、Aitermがその端末で動く前提が欠けた時の3種類だけ(PTYの依存、出力の置き場、AIのCLIの起動)。 通信の失敗(別端末へのSSH、AIのCLIとサービスの間、BugHubへの送信)、取消、待ちの時間切れは記録せず、呼んだ側へ理由の分かる返りで返す。 重さは、エラーの値や回数ではなく、起きた時の実害と自力で戻るかで決める。種類を足す時の決まりはADR 0102。

Read the full file on GitHub · 135 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago Changed · +7 lines · +344 tokens per session a1b09705dd61
  2. 7d ago Changed · +4 tokens per session f6108151f550
  3. 11d ago Changed · +5 tokens per session a8419610b1f0
  4. 14d ago Changed · +4 lines · +186 tokens per session 7c130a47fe1a
  5. 27d ago Changed · +38 tokens per session 1364dd5b08aa
  6. 1mo ago Changed · +3 lines · +160 tokens per session a20dbe0452e2
  7. 1mo ago Changed · +2 lines · +93 tokens per session 4cd1e9c2c8b3
  8. 1mo ago Changed · +5 lines · +245 tokens per session 5eca1d4bf806
  9. 1mo ago Changed · +5 tokens per session 3196f02dadef
  10. 1mo ago First seen · 114 lines · 2,815 tokens per session scan A e92e56a21a16

Subscribe to this mod's changes

aiterm-mcp AGENTS.md is an instructions file published in the GitHub repository kitepon/aiterm-mcp (6 stars, last pushed 3d ago), licensed MIT. It adds 3,895 tokens to every session, about $0.0156 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

aiterm-mcp AGENTS.md compared with instructions from other repositories

aiterm-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aiterm-mcp AGENTS.mdkitepon/aiterm-mcpInstructions file63d agoMITA3,895Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode