Borrowing it
Nothing to install: this file belongs to zv-louis/updsts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zv-louis/updsts/master/AGENTS.mdgit clone --depth 1 https://github.com/zv-louis/updstsWrote 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/zv-louis/updsts/agents-md)<a href="https://agentmods.dev/instructions/zv-louis/updsts/agents-md"><img src="https://agentmods.dev/badge/instructions/zv-louis/updsts/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.
<a href="https://agentmods.dev/instructions/zv-louis/updsts/agents-md"><img src="https://agentmods.dev/badge/instructions/zv-louis/updsts/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01445 | $0.01445 |
| Opus 5.5 | $0.00578 | $0.00578 |
| Sonnet 5.5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade C, and why
updsts AGENTS.md scanned grade C with 1 finding 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 23d 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- 既定の場所は `~/.aws/credentials` How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
updsts project
既存の AWS プロファイルと MFA の TOTP トークンから一時的な STS 認証情報を取得し、AWS の credentials ファイルを更新する CUI ツール兼ローカル MCP サーバー。 MCP 経由で操作される前提のため、アクセスキーやシークレットキーなどの秘密情報をマスクせずに LLM 側へ返さないことを設計上の原則としている。
技術スタック
- Python 3.12 以上、パッケージ管理は uv、ビルドは hatchling
- 主な依存:
boto3(STS のget_session_token)、fastmcp(MCP サーバー)、pydantic - テスト: pytest(マーカー:
slow/integration/unit/aws。AWS 呼び出しはモック)
ディレクトリ構成
src/updsts/
__main__.py CLI エントリポイント(main)。引数解析と例外のメッセージ化
cmdparam.py argparse のサブコマンド定義(get / list / mcp)
cmd_handler.py サブコマンドのハンドラ
awsutil.py 業務ロジック: credentials ファイルの読み込み、STS トークン取得、マスク処理
upcred.py CredentialUpdater: credentials ファイルの該当ブロックを書き換える
logutil.py ロガー(コンソール出力は stderr。MCP の stdio を汚さないため)
mcp_server.py FastMCP のツール定義(薄いラッパー)
mcp_impl.py MCP ツールの実装、例外を ValueError に揃える共通処理
src/updsts_main.py Claude プラグイン用の MCP 起動スクリプト(PEP 723 のインライン依存を持つ)
test/ モジュールごとの pytest
.claude-plugin/ Claude Code プラグインのマニフェスト
.mcp.json プラグイン用 MCP サーバー設定(uv run src/updsts_main.py mcp --mcp-server)
処理の流れは、CLI なら __main__.py → cmd_handler.py → awsutil.py → upcred.py、MCP なら mcp_server.py → mcp_impl.py → awsutil.py → upcred.py となる。
CLI
updsts get -n <profile> -t <totp_token> # STS 認証情報を取得して credentials ファイルを更新
updsts get -n <profile> -t <totp> -sn <sts_profile> # 書き込み先のプロファイル名を指定(既定は <profile>_sts)
updsts get -n <profile> -t <totp> -d 7200 # 有効期間(秒)を指定(既定は 3600)
updsts list # プロファイル一覧(秘密情報はマスク表示)
updsts mcp --mcp-server # MCP サーバーとして起動(オプションなしならツール一覧を表示)
共通オプションは -v, --verbose(0: 通常、1: 詳細、2: デバッグ)と -c, --credential_file。
MCP ツール
| ツール | 内容 |
|---|---|
updsts_update_sts_credential |
TOTP トークンで STS 認証情報を取得し、credentials ファイルを更新 |
updsts_get_credential_info |
指定プロファイルの情報(秘密情報はマスク済み) |
updsts_get_credential_info_list |
全プロファイルの情報(秘密情報はマスク済み) |
各ツールの cred_file と sts_profile_name は、空文字列なら既定値を使う。
TOTP トークンは mktotp などで生成する前提で、プロファイルの totp_secret_name がその対応付けに使われる。
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.
- 23d ago First seen · 90 lines · 1,445 tokens per session scan C b9b21b3cb444
updsts AGENTS.md is an instructions file published in the GitHub repository zv-louis/updsts (0 stars, last pushed 23d ago), licensed MIT. It adds 1,445 tokens to every session, about $0.0058 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.