build

A command that defines a step-by-step workflow for making well-scoped code changes with the user involved.

In plain words
What is it for?
It helps research the codebase, inspect failure modes, involve specialist agents, and plan and review an implementation.
Why use it?
It reduces misunderstandings by clarifying the target, success criteria, limits, risks, and edge cases before implementation.

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/ralfstrobel/agentic-brownfield-coding/build
Clone the repo
git clone --depth 1 https://github.com/ralfstrobel/agentic-brownfield-coding
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,246 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 $0.00017 $0.01246
Opus 5 $0.00009 $0.00623
Sonnet 5 $0.00003 $0.00249
Haiku 4.5 $0.00002 $0.00125

Measured yesterday against content hash ead0306aff17, 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.

claude-plugins/abc/commands/build.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.

Cooperative Development Request

The user wants to make the following complex additions / changes to the codebase: $ARGUMENTS

Adhere strictly to the following development workflow protocol.

Phase 1: Define

  1. Establish which repo components or sub-projects are target of the development (from user request or user role).
  2. Invoke any skills relevant to the development scope.
  3. Confirm the user's intent: the problem being solved, success criteria, what is out of scope, design constraints. Ask the user only about points the request and context leave genuinely unclear.

Phase 2: Research

  1. Use the project's specialized exploration subagents to locate all code parts relevant to the development request. Launch multiple exploration agents in parallel when the request spans different components or sub-projects.
  2. Pay special attention to system reminders that disclose additional context or skills upon reading files as such path-specific context is typically highly relevant. Invoke skills or read referenced files as suggested.

Phase 3: Challenge

Scrutinize the request based on the research findings. Probe at minimum:

  • Failure modes and edge cases.
  • Hidden complexity the request glosses over.
  • Security and invariants the existing architecture depends on.

Surface the resulting risks, assumptions, and open questions to the user, and resolve blocking ambiguities before moving on.

Phase 4: Strategize

Formulate between two and four different implementation approaches (one sentence summaries).

Think hard about this and intentionally vary approaches along dimensions that matter most in complex codebases:

  • Scope: How much existing code is modified vs. extended or wrapped around?
  • Conformity: Does the approach adopt existing structures, or does it introduce new concepts/abstractions?
  • Changeability: How easy will it be to modify the resulting code for new requirements?

Present the final approach options to the user to choose from or discuss.

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. yesterday First seen · 113 lines · 17 tokens per session scan A ead0306aff17

Subscribe to this mod's changes

build is a command published in the GitHub repository ralfstrobel/agentic-brownfield-coding (28 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,246 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.