build

build is a command for Claude Code from dinhnguyenngoc/spec-driven-claude-code. It costs 12 tokens per session (4,762 once invoked), scanned A, original, MIT.

An implementation command that completes planned tasks one at a time using Test-Driven Development, or TDD: write a failing test, make it pass, then improve the code. Each step leaves the project working and testable.

In plain words
What is it for?
Use it to implement planned features incrementally, add tests, run checks, and keep each vertical slice working from start to finish.
Why use it?
It catches mistakes close to where they are introduced and keeps unfinished work from spreading through the codebase. It also adapts its commands and tests to the project's technology stack.

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/dinhnguyenngoc/spec-driven-claude-code/build
Clone the repo
git clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-code

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/dinhnguyenngoc/spec-driven-claude-code/build.svg)](https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/build)
Your own site
<a href="https://agentmods.dev/commands/dinhnguyenngoc/spec-driven-claude-code/build"><img src="https://agentmods.dev/badge/commands/dinhnguyenngoc/spec-driven-claude-code/build.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,762 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 $0.00012 $0.04762
Opus 5 $0.00006 $0.02381
Sonnet 5 $0.00002 $0.00952
Haiku 4.5 $0.00001 $0.00476

Measured 4d ago against content hash a167f4dc5059, 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 4d 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 · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/build — Incremental Implementation

"The simplest thing that could work."

Purpose

Implement tasks one at a time using Test-Driven Development. Each increment leaves the system in a working, testable state.

Workspace Mode: if the session root declares Mode: workspace → resolve the target repo per CLAUDE.md §Workspace Mode before anything else; every path, probe, and gate below is relative to the target repo, and the workspace disk-check applies at the gate.

Stack Profile note: examples + commands below use the default profile (C#/.NET + SQL Server). Read Project Profile (.claude/PROJECT_PROFILE.md) first: Core = Node.jsrules/overrides/lang-nodejs.md + framework-nodejs-web.md + test-nodejs.md replace the language/framework/test layers — the dotnet commands in this file map to their npm equivalents (npm test, tsc --noEmit, npm run build; in-memory integration template per test-nodejs.md §Template A). Database ≠ SQL Serverrules/overrides/database-*.md (Oracle / MySQL / PostgreSQL / MongoDB) for data access + test setup. Brownfield: follow rules/brownfield.md (characterization test before modifying legacy code that has no tests).

Prerequisites

Required:

  • A plan exists — plans/plan.md (task detail: AC, Scenarios covered, NFRs covered (when the task delivers an NFR mechanism), Files to modify, Tests to add) + plans/todo.md (the actionable checklist)
  • Understanding of task acceptance criteria
  • The declared core's SDK installed — .NET SDK 8.0 (default) | Node.js 20 LTS (when the Profile declares Node core)

Optional (if available):

  • Pre-development security review (security/PRE_DEV_REVIEW.md from /secure) — if /secure was run, it must be marked APPROVED before building (Gate 4 is BLOCKING if run)
  • Threat model (security/THREAT_MODEL.md from /secure)

Agent Selection

Task Type Agent to Invoke
APIs, services, DB, background jobs 🔧 Backend Developer
Components, pages, routing, UI 🖥️ Frontend Developer

Read the full file on GitHub · 337 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. 4d ago First seen · 337 lines · 12 tokens per session scan A a167f4dc5059

Subscribe to this mod's changes

build is a command published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 4,762 once invoked, about $0.0001 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 2026-08-30.