Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/kitepon/aiterm-mcp/agents-mdgit clone --depth 1 https://github.com/kitepon/aiterm-mcpWrote 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.
[](https://agentmods.dev/instructions/kitepon/aiterm-mcp/agents-md)<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="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01735 | $0.01735 |
| Opus 5 | $0.00868 | $0.00868 |
| Sonnet 5 | $0.00347 | $0.00347 |
| Haiku 4.5 | $0.00173 | $0.00173 |
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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 86 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
- 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16 tools。PTY 6、標準
agent_launch1、deprecated互換launcher 4、agent_configure、agent_steer、claude_turn、claude_approval、diagnosticsである。 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Grok CLIのmodel presetである。- 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。完了はreceiptの
wait_processを別processとして起動し、outcomeを判定する。親自身のturnをforeground waiterで止めない。回答回収はpty_read(agent_transcript:true)またはclaude_turn recoverを使い、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、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。
コード所有
src/index.ts: MCP toolとschema。src/core.ts: PTY、入出力整形、出力削減、完了検出、harness共通進行。src/harnesses/: Claude/Codex/Grok/Cursor固有の起動、ready、完了、transcript、catalog。src/agent-shared.ts/src/state-root.ts: harness中立の相関state。src/tmux-runtime.ts/src/psmux-send-worker.ts/src/agent-resolver.ts: OS・multiplexer差。src/runtime-error-*.ts: 製品所有のoffline error aggregate。src/rtk.ts: 自前reducer。pytestはrtk 0.42.0と一致し、FAILED理由全文保持だけ意図的に異なる。prototype/python/: 旧MVPとreducer移植元。参照専用。
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.
- today Changed · +34 tokens per session 3f251d610497
- 3d ago Changed · +4 tokens per session 688305ccc7d7
- 4d ago First seen · 86 lines · 1,697 tokens per session scan A 6c8b9d9b212f
aiterm-mcp AGENTS.md is an instructions file published in the GitHub repository kitepon/aiterm-mcp (5 stars, last pushed today), licensed MIT. It adds 1,735 tokens to every session, about $0.0087 per session on Opus 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.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
mistral-mcp CLAUDE.md
Instructions for Swih/mistral-mcp, covering claude.md — mistral-mcp, 1. identité du projet, 2. règles dures (ne pas transgresser), 3. layout & responsabilités and 4. conventions de code.
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.
trello-mcp AGENTS.md
AGENTS.md instructions for enthouan/trello-mcp, covering agents.md, project summary, hard constraints, runtime and package manager and common commands.
swag-mcp CLAUDE.md
Claude Code instructions for jmagar/swag-mcp, covering swag mcp - claude memory reference, project overview, core architecture, key components and common development commands.