build

A command that imposes a multi-stage process for complex coding tasks, from analysis and design through implementation, review, and reflection.

In plain words
What is it for?
Use it to structure complex changes, get agreement on the design, track each phase, review the result, and document follow-up work.
Why use it?
It prevents code from being written before the task is understood and keeps decisions and progress recorded in a notes file.

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/lhohan/claude-code-plugins/build
Clone the repo
git clone --depth 1 https://github.com/lhohan/claude-code-plugins
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,150 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 $0.00020 $0.02150
Opus 5 $0.00010 $0.01075
Sonnet 5 $0.00004 $0.00430
Haiku 4.5 $0.00002 $0.00215

Measured yesterday against content hash 99862996c180, 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.

hanlho-cmds/commands/build.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task

The task you are helping me with is described in {{prompt}} .

System

When executing a task, NEVER begin writing code immediately. Always start with analysis and planning. Verify understanding of the task with the user BEFORE proposing implementation details.

Task Execution Process

Follow these steps in STRICT ORDER:

Setup

BEFORE beginning: create a new markdown file to capture your notes while you work on this issue. Save it in the notes directory with the same name as the markdown file passed: {{prompt}} . IF such a file already exists, read the file and continue from where you left off.

Required Notes File Structure

Your notes file MUST include these standardized sections for session continuity:

## Current Status
- **Phase**: [Current phase number and name]
- **Step**: [Current step within phase]
- **Last Updated**: [Timestamp]

## Phase Status Tracker
- ⏸️ Phase 1: Task Analysis - PENDING
- ⏸️ Phase 2: Solution Design - PENDING
- ⏸️ Phase 3: Implementation - PENDING
- ⏸️ Phase 4: Review - PENDING
- ⏸️ Phase 5: Submit - PENDING
- ⏸️ Phase 6: Iterate - PENDING
- ⏸️ Phase 7: Reflect - PENDING
- ⏸️ Phase 8: Clean Up - PENDING

Status Icons: ⏸️ PENDING | 🔄 IN PROGRESS | ✅ COMPLETED

Phase 1: Task Analysis

BEFORE STARTING: Update notes with "Phase 1: Task Analysis - IN PROGRESS 🔄"

  1. Load the task described in {{prompt}}.
  2. Summarize the task requirements and constraints in your own words
  3. Challenge requirements early. Always question whether the requested task or approach is correct and necessary
  4. Explicitly ask the user to confirm your understanding before proceeding
  5. Identify any ambiguities or points requiring clarification and ask about them
  6. Once your understanding of the issue has been confirmed, write a summary to your note file.

AFTER COMPLETION: Update notes with "Phase 1: Task Analysis - COMPLETED ✅"

Optional: Consider using research agents for codebase understanding if the task involves unfamiliar systems

Read the full file on GitHub · 188 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 · 188 lines · 20 tokens per session scan A 99862996c180

Subscribe to this mod's changes

build is a command published in the GitHub repository lhohan/claude-code-plugins (2 stars, last pushed 9mo ago), licensed MIT. It adds 20 tokens to every session and 2,150 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 2026-08-31.