dtc-mcp: Command for Claude Code

.claude/commands/bench.md

bench is a command for Claude Code from rafaelsztutman/dtc-mcp. It costs 31 tokens per session (2,115 once invoked), scanned A, original, MIT.

A command for running batches of tests that compare two MCP setups, including how they handle conversations of different lengths.

In plain words
What is it for?
Use it to run the baseline, short, medium, or long conversation benchmark batches, with optional retries.
Why use it?
It records benchmark results in one run so you can compare performance without manually starting each test.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

This is rafaelsztutman/dtc-mcp's own configuration. It tells Claude Code how to work on dtc-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 dtc-mcp configures →

Part of the dtc-mcp plugin — 2 skills, 4 commands shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to rafaelsztutman/dtc-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/rafaelsztutman/dtc-mcp/main/.claude/commands/bench.md
Clone the repo
git clone --depth 1 https://github.com/rafaelsztutman/dtc-mcp

Made for: Claude Code.

Or install dtc-mcp, the plugin that ships this one along with the rest of its 2 skills, 4 commands.

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 bench

README.md
[![agentmods](https://agentmods.dev/badge/commands/rafaelsztutman/dtc-mcp/bench/github.svg)](https://agentmods.dev/commands/rafaelsztutman/dtc-mcp/bench)
Your own site
<a href="https://agentmods.dev/commands/rafaelsztutman/dtc-mcp/bench"><img src="https://agentmods.dev/badge/commands/rafaelsztutman/dtc-mcp/bench/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 bench

Your own site · 80×15
<a href="https://agentmods.dev/commands/rafaelsztutman/dtc-mcp/bench"><img src="https://agentmods.dev/badge/commands/rafaelsztutman/dtc-mcp/bench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,115 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00031 $0.02115
Opus 5 $0.00015 $0.01058
Sonnet 5 $0.00006 $0.00423
Haiku 4.5 $0.00003 $0.00212

Measured 8d ago against content hash 6c7d2ca55924, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bench 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 8d 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.

.claude/commands/bench.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bench — head-to-head MCP benchmark driver

You are about to execute one batch of the dtc-mcp vs Klaviyo-MCP benchmark. The benchmark is organized along the conversation-length axis: 1-turn baseline, 2-turn short, 5-turn medium, 10-turn long. The hypothesis is that MCPs not designed for conversation continuity pay a compounding cost as turns grow, so dtc-mcp's stateful sandbox should outperform tool-list MCPs more sharply at longer conversations.

Execution model: every cell — single-turn or multi-turn — is run via tsx bench/runner/cli.ts multiturn --cell <cellId>. That command spawns ONE claude -p --input-format stream-json process, feeds it the cell's prompts over stdin, parses the streamed output for per-turn responses + aggregate usage, then records the result. One claude process = one MCP transport, so dtc-mcp's per-connection sandbox state persists across the whole trajectory (the empirically-verified property that motivates the whole benchmark).

Grading is deferred to a separate LLM-as-judge phase after recording — there is no per-cell grading during a batch run.

Args

  • --batch <A|B|C|D> (default: A) — which batch to run
    • A = baseline (1 turn) × 3 tasks × 2 MCPs × 2 trials = 12 cells
    • B = short (2 turns) × 2 tasks × 2 MCPs × 2 trials = 8 cells
    • C = medium (5 turns) × 2 tasks × 2 MCPs × 2 trials = 8 cells
    • D = long (10 turns) × 2 tasks × 2 MCPs × 2 trials = 8 cells
  • --retry <cellId> — re-run one failed/invalid cell, ignore others
  • --limit N — only run the first N pending cells (useful for smoke tests)

How to execute

  1. Verify the run is initialized. If bench/results/ has no recent state.json, instruct the user to run tsx bench/runner/cli.ts init first and stop.

  2. Verify both MCPs are configured at the user level (~/.claude.json mcpServers) so the spawned claude -p child process sees them. There should be both dtc-mcp (or whatever they named it) and klaviyo (or similar). If not, instruct the user to add the missing one and stop.

Read the full file on GitHub · 170 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. 8d ago First seen · 170 lines · 31 tokens per session scan A 6c7d2ca55924

Subscribe to this mod's changes

bench is a command published in the GitHub repository rafaelsztutman/dtc-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 2,115 once invoked, about $0.0002 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.