A command that guides a software project from initial intake through planning, implementation, testing, and CI preparation. CI, or continuous integration, automatically checks changes as they are added to a project.

Use it to take a new project from an initial brief to a tested, documented application ready for CI. It includes setup for a monorepo, which is one repository containing multiple related parts of a project.

It keeps the major project stages in order and requires approval of the plan before the build starts. It also coordinates frontend, backend, integration, testing, and documentation work.

engineer — Command for Claude Code by martian56/claude-engineer

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.

Clone the repo

git clone --depth 1 https://github.com/martian56/claude-engineer

Made for: Claude Code.

Or install claude-engineer, the plugin that ships this one along with the rest of its 13 skills, 1 command, 2 agents, 3 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/martian56/claude-engineer/engineer/github.svg)](https://agentmods.dev/commands/martian56/claude-engineer/engineer)

Your own site

<a href="https://agentmods.dev/commands/martian56/claude-engineer/engineer"><img src="https://agentmods.dev/badge/commands/martian56/claude-engineer/engineer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/martian56/claude-engineer/engineer"><img src="https://agentmods.dev/badge/commands/martian56/claude-engineer/engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 483 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00037	$0.00483
Opus 5.5	$0.00015	$0.00193
Sonnet 5.5	$0.00007	$0.00097
Haiku 4.5	$0.00004	$0.00048

Measured 1mo ago against content hash f7543bbc75f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

engineer 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 1mo 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.

plugins/claude-engineer/commands/engineer.md · 26 lines

What it actually says

/claude-engineer:engineer - guided lifecycle

Drive a full greenfield project from idea to a tested, documented, CI-ready app. Follow the stages in order; do not skip the plan sign-off gate. Invoke the named skills (don't freelance a stage).

If $ARGUMENTS is provided, treat it as the starting brief or a path to one.

Run these stages in order

Conventions & scaffold - claude-engineer:project-conventions, then claude-engineer:monorepo-and-tooling and claude-engineer:docker-dev-environment for the skeleton.
Intake - claude-engineer:intake-project (refine/created brief; uses superpowers:brainstorming).
Plan - claude-engineer:plan-project (phased docs/plan/*; uses superpowers:writing-plans). STOP for the user's explicit sign-off before any build.
Memory - claude-engineer:project-memory (init .claude-engineer/ state).
Build (autonomous) - claude-engineer:execute-build in CX-first order: design-system → frontend-development → backend-development → integration. Orchestrate with superpowers:subagent-driven-development (each task uses superpowers:test-driven-development).
Quality - claude-engineer:testing-and-quality (run the four gates; verify with evidence).
CI & finish - claude-engineer:ci-cd-pipeline, then superpowers:finishing-a-development-branch.

Rules

Plan-gated then autonomous: after sign-off, run to completion; stop only on genuine blockers.
Update .claude-engineer/progress.md after each task and memory.md on each decision.
Nothing is "done" until all four quality gates pass with fresh evidence.

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.

1mo ago First seen · 26 lines · 37 tokens per session scan A f7543bbc75f2

Subscribe to this mod's changes

engineer is a command published in the GitHub repository martian56/claude-engineer (2 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 483 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Planning Testing autonomous-agent claude-code-marketplace claude-code-plugin claude-skills design-system

fidelity

Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a letter grade, a ranked correction plan, and a shareable card.

Manavarya09/design-extract · 40 tokens

apex

APEX Methodology - The systematic Analyze-Plan-Execute-eLicit-eXamine approach for intelligent development. Reduces hallucination and defect risk through mandatory parallel research, self-review, and validation gates.

fusengine/agents · 42 tokens

test

Test commit. Use for add tests, update tests, test coverage, unit test, spec.

fusengine/agents · 19 tokens

improve-test-quality

Analyze and improve existing test quality with better assertions, coverage, and maintainability.

sigistry/marketplace · 15 tokens

test-gap-analysis

Identify untested code paths and missing test coverage across the codebase.

sigistry/marketplace · 13 tokens

validate

Mechanically validate the sonu plugin repo before a PR — manifest sync, YAML frontmatter, shell-fence syntax, named-source and AI-attribution scans, cross-reference integrity, skill reachability. Only meaningful inside the claude-plugins repo; in any other repo, say so and stop.

PrabhdeepSingh/claude-plugins · 60 tokens