mcp-ui-poc: Command for Claude Code

.claude/commands/start.md

start is a command for Claude Code from iamadi11/mcp-ui-poc. It costs 0 tokens per session (1,866 once invoked), scanned A, original, MIT.

An end-to-end development command that chooses a feature, researches it, plans the work, implements it, tests it, checks it in a browser, and deploys it. QA means checking that the result works as intended.

In plain words
What is it for?
Use it to take a selected feature from discovery through deployment. It covers planning, coding, automated checks, browser testing, user critique, committing, and release.
Why use it?
It puts the development steps into one repeatable sequence, reducing skipped research, testing, documentation, or validation. It also compares the implementation with the actual codebase.

Command for Claude Code

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

This is iamadi11/mcp-ui-poc's own configuration. It tells Claude Code how to work on mcp-ui-poc 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 mcp-ui-poc configures →

Reuse

Borrowing it

Nothing to install: this file belongs to iamadi11/mcp-ui-poc. 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/iamadi11/mcp-ui-poc/main/.claude/commands/start.md
Clone the repo
git clone --depth 1 https://github.com/iamadi11/mcp-ui-poc

Made for: Claude Code.

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 start

README.md
[![agentmods](https://agentmods.dev/badge/commands/iamadi11/mcp-ui-poc/start.svg)](https://agentmods.dev/commands/iamadi11/mcp-ui-poc/start)
Your own site
<a href="https://agentmods.dev/commands/iamadi11/mcp-ui-poc/start"><img src="https://agentmods.dev/badge/commands/iamadi11/mcp-ui-poc/start.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,866 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01866
Opus 5 $0.00000 $0.00933
Sonnet 5 $0.00000 $0.00373
Haiku 4.5 $0.00000 $0.00187

Measured 6d ago against content hash 3e206e8a3dcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

start 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 6d 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/start.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/start

Autonomous end-to-end cycle: discover and choose one feature → research → plan → implement → QA (automated + MCP browser manual testing) → brutal user critique → commit → deploy.

Always follow docs/AI_WORKFLOW.md (Research → Plan → Test definition → Implement → Tests & checks → Validate → Document → Instrument). Do not skip steps without a one-line rationale.

Source of truth

  • The codebase is the source of truth for behavior, APIs, patterns, and what is actually shipped. Read and trace real code paths before deciding what to build.
  • README.md (and CLAUDE.md, docs/AI_WORKFLOW.md) supply product intent, structure overview, ports, and scripts — use them to understand what this project is supposed to do and how to run it.
  • If README and code disagree (endpoints, flows, folder layout), follow the code and note the doc drift only if you fix docs in scope.

Phase A — Project context, then auto-collect and pick a feature

Run this before writing implementation code.

A1 — Understand the project (codebase first, README second)

  1. Codebase (mandatory) — Establish how the app actually works:
    • Entry points: e.g. server/index.js, client/src/main.jsx, client/src/App.jsx (adjust if the repo differs).
    • Trace server/ routes, MCP-related modules, and client/src/ UI flow enough to describe the main user journey in plain language.
    • Use explore-codebase when layout or dependencies are unclear; prefer scoped search under server/ and client/ per docs/AI_WORKFLOW.md.
  2. README + project docs — Read README.md for feature list, API summary, ports, and install/run steps; skim CLAUDE.md and docs/AI_WORKFLOW.md for workflow and boundaries.
  3. Synthesize — In your working notes, write a short “what this project does” paragraph grounded in code + README (not generic stack guesses). This is the lens for every later step.

Read the full file on GitHub · 113 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. 6d ago First seen · 113 lines · 0 tokens per session scan A 3e206e8a3dcd

Subscribe to this mod's changes

start is a command published in the GitHub repository iamadi11/mcp-ui-poc (8 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,866 tokens. 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.