build

build is a command for Claude Code from GuillemRoca/agent-skills-android. It costs 0 tokens per session (430 once invoked), scanned A, original, MIT.

A command for implementing the next development task with test-driven development, or TDD: writing a test for the expected behavior before writing the code that passes it.

In plain words
What is it for?
Use it to work through tasks interactively or in an approved automatic run, adding tests, implementing the smallest matching change, and verifying the result.
Why use it?
It breaks larger work into smaller verified steps and checks that tests and the application build still succeed after each step.

Command for Claude Code

Part of the agent-skills-android plugin — 29 skills, 7 commands, 3 agents, 1 hook shipped together

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/guillemroca/agent-skills-android/build
Clone the repo
git clone --depth 1 https://github.com/GuillemRoca/agent-skills-android

Made for: Claude Code.

Or install agent-skills-android, the plugin that ships this one along with the rest of its 29 skills, 7 commands, 3 agents, 1 hook.

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/guillemroca/agent-skills-android/build.svg)](https://agentmods.dev/commands/guillemroca/agent-skills-android/build)
Your own site
<a href="https://agentmods.dev/commands/guillemroca/agent-skills-android/build"><img src="https://agentmods.dev/badge/commands/guillemroca/agent-skills-android/build.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 430 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 $0.00000 $0.00430
Opus 5 $0.00000 $0.00215
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured 4d ago against content hash 9cd64960c852, 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 · 49 lines

What it actually says

/build — Incremental Implementation with TDD

Build the next task incrementally using test-driven development.

Modes

  • /build — interactive: work task by task, checking in between tasks.
  • /build auto — autonomous: plan the remaining tasks first, present the full plan for ONE approval, then implement every task without further check-ins. Stop and ask only on: failing tests you cannot fix within the task's scope, a needed deviation from the approved plan, or destructive operations. Everything else follows the same per-task cycle below.

Instructions

Load and follow these skills:

  • incremental-implementation from skills/incremental-implementation/SKILL.md
  • test-driven-development from skills/test-driven-development/SKILL.md

Per-Task Cycle

For each task in tasks/todo.md:

  1. Review the task's acceptance criteria
  2. Gather examples — find similar patterns in the codebase
  3. Write a failing test (RED) — describes the expected behavior
  4. Write minimal code to pass the test (GREEN)
  5. Run ./gradlew test — verify all tests pass
  6. Run ./gradlew assembleDebug — verify the build succeeds
  7. Verify the slice end-to-end when it is user-visible — run its Maestro flow per android-e2e-verification (maestro test .maestro/<slice>.yaml)
  8. Commit the increment
  9. Repeat for the next acceptance criterion

Error Handling

If a test fails unexpectedly or the build breaks:

  • Load debugging-and-error-recovery skill
  • Follow the six-step triage process
  • Fix the root cause before proceeding

Rules

  • Each increment leaves the codebase in a working state
  • Never skip the build check between increments
  • Commits are small and focused (~100 lines)
  • Incomplete features go behind feature flags
  • Don't mix refactoring with feature work
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 · 49 lines · 0 tokens per session scan A 9cd64960c852

Subscribe to this mod's changes

build is a command published in the GitHub repository GuillemRoca/agent-skills-android (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 430 tokens. 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.