build

A command that starts an artifact-driven development workflow. It creates task, implementation-plan, and verification documents, plus records important architecture decisions.

In plain words
What is it for?
It is for starting or continuing structured builds, tracking tasks, documenting architecture decisions, and recording verification results.
Why use it?
It gives a project a written scope, technical approach, progress record, and proof of completion instead of relying only on conversation or code changes.

Command

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/alteredcraft/claude-code-plugins/build
Clone the repo
git clone --depth 1 https://github.com/AlteredCraft/claude-code-plugins
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,909 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 $0.00006 $0.01909
Opus 5 $0.00003 $0.00955
Sonnet 5 $0.00001 $0.00382
Haiku 4.5 $0.00001 $0.00191

Measured yesterday against content hash c0dba61d3ec4, 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 yesterday.

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.

plugins/artifact-workflow/commands/build.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are executing an artifact-driven development workflow inspired by Google's Antigravity. This workflow produces three living artifacts that scope work and track progress.

Artifacts Location

Per-build artifacts live in ./.artifacts/bld-<project-slug>/:

  • todo.md — Task list (scope and progress)
  • implementation-plan.md — Technical approach (architecture)
  • walkthrough.md — Verification record (proof of completion)

Shared artifact at ./.artifacts/ADR.md:

  • Architecture Decision Records — significant decisions across all builds, each entry links to its related build

Phase Detection

First, check if .artifacts/ directory exists and contains any bld-* folders (Search(pattern: ".artifacts/bld-*/**/*")).

If existing builds are found:

  1. STOP — List all existing bld-* folders to the user
  2. Ask: "I found these existing builds. Would you like to:
    • Continue one of these? (specify which)
    • Start a new build?"
  3. Wait for user response before proceeding

If user chooses to continue an existing build:

Read the artifacts in that folder to determine current phase:

  1. todo.md exists, status: in-progress → Continue task list refinement or proceed to planning
  2. implementation-plan.md exists, status: pending → Await user approval
  3. implementation-plan.md exists, status: in-progress → Continue execution
  4. walkthrough.md exists, status: complete → Workflow finished, summarize

If user chooses to start a new build (or no existing builds found):

If .artifacts/ directory does not exist, create it and add:

  1. A README.md that explains:
    • What this directory is for (managed by the /build command)
    • The three per-build artifacts (todo.md, implementation-plan.md, walkthrough.md)
    • The shared ADR.md file for architecture decisions across all builds
    • A brief summary of the workflow phases
    • How to use the /build command
  2. An ADR.md file with this template:
    # Architecture Decision Records
    
    This file captures significant architectural decisions made during builds in this project.
    
    ---
    

Read the full file on GitHub · 180 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. yesterday First seen · 180 lines · 6 tokens per session scan A c0dba61d3ec4

Subscribe to this mod's changes

build is a command published in the GitHub repository AlteredCraft/claude-code-plugins (13 stars, last pushed 3mo ago), licensed MIT. It adds 6 tokens to every session and 1,909 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 2026-08-30.