build

build is a command for Claude Code from MDGrey33/claude_mind. It costs 8 tokens per session (827 once invoked), scanned A, original, MIT.

A command that coordinates a software project through planning, design, coding, testing, security review, and deployment, while storing task information in a shared workspace.

In plain words
What is it for?
Use it to start an end-to-end build from a written request and organize specifications, architecture, implementation, tests, security checks, and deployment work.
Why use it?
It gives a development task a defined sequence and keeps the work from being scattered across separate steps or agents.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/mdgrey33/claude_mind/build
Clone the repo
git clone --depth 1 https://github.com/MDGrey33/claude_mind

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 build

README.md
[![agentmods](https://agentmods.dev/badge/commands/mdgrey33/claude_mind/build.svg)](https://agentmods.dev/commands/mdgrey33/claude_mind/build)
Your own site
<a href="https://agentmods.dev/commands/mdgrey33/claude_mind/build"><img src="https://agentmods.dev/badge/commands/mdgrey33/claude_mind/build.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 827 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 $0.00008 $0.00827
Opus 5 $0.00004 $0.00413
Sonnet 5 $0.00002 $0.00165
Haiku 4.5 $0.00001 $0.00083

Measured 3d ago against content hash 7bbe7a992427, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

build 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 3d 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/build.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Command

Start the autonomous development cycle for: $ARGUMENTS

Your Mission

You are the Chief of Staff. Orchestrate the development team through all phases to deliver production-ready software.

Detailed Workflow

@import ../docs/workflow.md

Step 1: Initialize Workspace

mkdir -p .claude-workspace/{specs,architecture,implementation,tests,security,deployment,deliverables}

TASK_ID="task-$(date +%Y%m%d-%H%M%S)"
TIMESTAMP=$(date -u +%Y-%m-%dT%H:%M:%SZ)

cat > .claude-workspace/current-task.json << EOF
{
  "task_id": "$TASK_ID",
  "user_request": "$ARGUMENTS",
  "status": "planning",
  "created_at": "$TIMESTAMP",
  "iterations": 0,
  "confidence": 0
}
EOF

Step 2: Execute Phases

Use Task tool to invoke agents sequentially:

Phase 1: Planning

subagent_type: technical-pm
prompt: Create specification from the user request. Write to .claude-workspace/specs/

Phase 2: Architecture

subagent_type: senior-architect
prompt: Design architecture based on specification. Write to .claude-workspace/architecture/

Phase 3: Implementation

Implementation Standards:

  • All API URLs must be configurable via environment variables
  • Default to http://localhost:3000 for development
  • Create .env.example with all required environment variables
  • Never hardcode URLs, ports, or secrets in source code

Run in parallel:

subagent_type: lead-backend-engineer
prompt: |
  Implement backend. Write to .claude-workspace/implementation/backend/

  REQUIRED: Make all API URLs configurable:
  - Use environment variables (e.g., API_BASE_URL, PORT)
  - Default PORT to 3000 for development
  - Create .env.example documenting all env vars
  - Include sample values (not real secrets)

subagent_type: frontend-engineer (if needed)
prompt: |
  Implement frontend. Write to .claude-workspace/implementation/frontend/

  REQUIRED: Make all API URLs configurable:
  - Use environment variables (e.g., REACT_APP_API_URL, VITE_API_URL)
  - Default to http://localhost:3000 for development
  - Create .env.example documenting all env vars

Read the full file on GitHub · 130 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. 3d ago First seen · 130 lines · 8 tokens per session scan A 7bbe7a992427

Subscribe to this mod's changes

build is a command published in the GitHub repository MDGrey33/claude_mind (2 stars, last pushed 8mo ago), licensed MIT. It adds 8 tokens to every session and 827 once invoked, about $0.0000 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.