Borrowing it
Nothing to install: this file belongs to standardbeagle/mcp-tui. 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/standardbeagle/mcp-tui/main/AGENTS.mdgit clone --depth 1 https://github.com/standardbeagle/mcp-tuiWrote 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/standardbeagle/mcp-tui/agents-md)<a href="https://agentmods.dev/instructions/standardbeagle/mcp-tui/agents-md"><img src="https://agentmods.dev/badge/instructions/standardbeagle/mcp-tui/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/standardbeagle/mcp-tui/agents-md"><img src="https://agentmods.dev/badge/instructions/standardbeagle/mcp-tui/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 | $0.03848 | $0.03848 |
| Opus 5.5 | $0.01539 | $0.01539 |
| Sonnet 5.5 | $0.00770 | $0.00770 |
| Haiku 4.5 | $0.00385 | $0.00385 |
Grade A, and why
mcp-tui AGENTS.md scanned grade A 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 以 curl 驗 HTTP/SSE server；查 CLI timeout 是否干涉；確 stdio command 過 validation。 How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
此檔示 coding agents 於本倉作業之準則。規則詳見 .claude/rules/；項目概要見 .claude/CLAUDE.md；術語見 .claude/rules/glossary.md。
Project Overview
MCP-TUI，Go 製 Model Context Protocol (MCP) servers 測試客戶端；兼 interactive TUI (bubbletea) 與 scriptable CLI (cobra)。支 stdio、SSE、streamable HTTP transports；可 browse/execute tools、resources、prompts，應 sampling、elicitation、roots，行 OAuth，並以 verify/conform 驗 server 合規。發佈為 release binaries 及 @standardbeagle/mcp-tui npm wrapper。
Agent Setup
- 本倉不直配 MCP servers（無
.mcp.json，settings 無 mcpServers）。Agent 所需 MCP 皆經 slop-mcp。 examples/*.json為 mcp-tui 之輸入樣本，非 agent 配置。- Task 系統：worktrack。dartai 已廢。
Development Commands
凡 test/build 皆經 tman（.tman.kdl；aliases 映 CI jobs）：
./build # go build -o bin/mcp-tui .
./test # go test ./... -timeout 15m (CI "test")
tman race # go test -race ./internal/... -timeout 20m (CI "race")
tman vet # go vet ./...
tman lint # golangci-lint v2.13.2，經 go run 釘版，毋全域裝 (CI "lint")
make ci # vet + fmt-check + lint + test + race
- 敗則讀
.tman/<alias>.fail.log，毋重跑全套。 - 整合測試需
npx（server-everything）與pwsh；CI 設MCP_TUI_REQUIRE_PWSH=1，缺 pwsh 則敗而非略。 gofmt與 lint 皆為 CI 閘；lint 須 0 issues。nolint唯用於誤報或改之反損可讀，必附具體理由；勿為藏 issue 而升.golangci.yml之閾。
Architecture
main.go cobra root；註 tool/task/resource/prompt/server/capabilities/verify/conform
internal/cli/ subcommands (cmd_*.go, tool.go)；base.go 共 connection flags；oauth_flags.go 註 --oauth-*
conform/ verify/ 規格情景與安全探針（conform 之 verify 情景取自 verify.AllProbes）
internal/mcp/ service layer（service.go）包 go-sdk client
mrtr.go mrtr_elicit.go 自行之 multi round-trip 迴圈（SDK 迴圈停用），每輪記錄
list_cache.go SEP-2549 list cache 觀測；handshake_trace.go 記版本協商
resource_subscriptions.go server_log_level.go traceparent.go tasks.go message_log.go ...
protocol/ 葉包：StatelessVersion（2026-07-28）判定
inputschema/ tool inputSchema 經 $ref、T|null 解析（CLI 與 TUI 共用）
tasks/ MCP tasks 二 wire form；sdk.go 為唯一觸 SDK 內部之檔
wiretap/ 唯一觀線處：stdio/in-memory 包 connection，HTTP 經 RoundTripper 讀 request/response body（含 SSE），stdio 另逐行讀 stdout 以見 SDK decoder 所拒之行；tasks link 與 protocol watcher 為其 Observer
protocolwatch/ 判 server 違 JSON-RPC 2.0／所協商版本之訊息（無主 id、重複回應、未定義 method、非 JSON-RPC）；method 表在 protocol/methods.go
transports/ factory.go 依 TransportType 造 SDK transport；context.go 定 context strategy
oauth/ sampling/ elicitation/ roots/ notifications/ session/ ...
internal/redact/ 唯一去敏模組：headers、URLs、bodies、錯誤文、MCP payloads
internal/tui/ app/（app.go、manager.go）、screens/、models/（connections.go：file discovery）、components/
internal/config/ config 解析、ValidateCommand
internal/debug/ logger、buffer、httptrace.go（HTTP 追蹤）、slog.go（SDK slog 橋）、errors.go（具名錯誤碼）
internal/mcp/debug 有 event tracer 與 replay
internal/platform/signal 跨平台 signal handling
internal/testutil/ listener、pwsh helpers、streamable HTTP server、TaskServer
test-servers/ 故障 MCP servers（crash、timeout、oversized…）供韌性測試
docs/ Astro docs site（dev.standardbeagle.com）
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.
- 1mo ago Changed · -101 lines · +1,819 tokens per session b59641dc7220
- 2mo ago First seen · 232 lines · 2,029 tokens per session scan A 66fd2301f4fc
mcp-tui AGENTS.md is an instructions file published in the GitHub repository standardbeagle/mcp-tui (12 stars, last pushed 5d ago), licensed MIT. It adds 3,848 tokens to every session, about $0.0154 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.