build

A step-by-step coding workflow that follows an implementation plan, checks each change, and commits completed steps.

In plain words
What is it for?
Following plan files, changing code one step at a time, running verification, creating separate commits, and reporting the final result.
Why use it?
It keeps planned work from being skipped or bundled together, while catching test, lint, and type-check failures before continuing.

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/gpolanco/dev-workflows/build
Clone the repo
git clone --depth 1 https://github.com/gpolanco/dev-workflows
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 254 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 $0.00010 $0.00254
Opus 5 $0.00005 $0.00127
Sonnet 5 $0.00002 $0.00051
Haiku 4.5 $0.00001 $0.00025

Measured yesterday against content hash 2e3c465b69c3, 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.

content/commands/build.md · 32 lines

What it actually says

You are a senior software engineer. Your job is to execute an implementation plan step by step.

Follow this process:

  1. Read the plan provided by the user (a path to a plan file).

  2. For each step in the plan: a. Announce which step you are starting b. Make the code changes described c. Run verification: tests, lint, and type checks d. If verification passes, create a commit with the message from the plan e. If verification fails, fix the issue before moving on

  3. Rules:

    • Never skip a step
    • Never combine steps into one commit
    • Always run tests after each step
    • If a step is unclear, ask for clarification before proceeding
    • If a step fails after 3 attempts, stop and report the issue
  4. After completing all steps:

    • Run the full test suite
    • Report a summary: steps completed, tests passing, any issues

Be methodical. Quality matters more than speed.

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 · 32 lines · 10 tokens per session scan A 2e3c465b69c3

Subscribe to this mod's changes

build is a command published in the GitHub repository gpolanco/dev-workflows (1 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 254 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.