Skip to main content
subagent CX Codex

coder · ruvnet — Claude Code subagent: coding and installation

The coder subagent implements and refactors code, designs APIs, and handles errors. Use it for development tasks that call for tests and follow-up checks.

no license ★ 850 updated 2026-10-26

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/coder.md
Open on GitHub

What coder does

coder reviews requirements, plans architecture and interfaces, then builds functionality incrementally. Its guidance favors readable code, error handling, and writing tests before implementation. It can also refactor existing code while preserving its behavior.

Before a task, hooks search npx claude-flow memory for similar successful patterns and past failures, then record that work has started. Afterward, the subagent runs npm run lint --if-present when the project contains package.json, and runs npm test. A project without a configured test command can therefore fail at this check. Results are stored in memory; a successful run with more than 90 tests triggers neural pattern training.

What it helps with

  • implement a feature from project requirements
  • design an API interface
  • refactor code while keeping its behavior
  • add error handling and tests

Example prompts for the agent

  • Implement error handling for this API and add tests.
  • Design and build a service interface from the project requirements.
  • Refactor this module without changing what it does.

How to install coder

Manually: put the files in place

.claude/agents/coder.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about coder

How do I install coder in Claude Code?

Add the subagent file at .claude/agents/coder.md.

What does the coder subagent do?

It implements and refactors code, designs APIs, and handles errors. It also runs checks and stores information about completed work.

Which checks does coder run after a task?

If the project has package.json, it runs npm run lint --if-present. It then runs npm test.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

coder by other authors comes first.

coder josstei coder — a subagent for turning specifications into production code. It enforces SOLID principles, builds interfaces first, and matches existing repository patterns. CX Codex ★ 489repo stars ts-coder sno-ai The ts-coder Claude Code skill guides TypeScript and TSX implementation and refactoring within an existing repository. It applies to work on types, APIs, and migrations. CX Codex +1 ★ 869repo stars zero-hallucination-coder Alireza Rezvani zero-hallucination-coder runs an engineering loop across five strict phases to prevent invented APIs, broken imports, and bloated code. Ideal for schema changes, auth rewrites, and multi-file tasks. CX Codex +1 69installs ns-coder nextstage-brasil ns-coder handles focused code changes such as fixes, small refactors, scripts, and migrations. Use it for ad-hoc work outside a multi-stage SDD handoff. CX Codex +1 151installs backend-security-coder rmyndharis backend-security-coder is a Claude Code skill for writing secure backend code and reviewing security-sensitive changes. It covers input checks, authentication, and API protection. CX Codex +1 142installs backend-api-security-backend-security-coder Seth Hobson backend-api-security-backend-security-coder is a Claude Code subagent that writes defensive backend code and validates API input. It supports endpoint implementation and vulnerability fixes. CX Codex ★ 42,780repo stars karpathy-coder claude-code-skills karpathy-coder is a Claude Code skill that checks code against four Karpathy principles: surface assumptions, keep changes simple, limit edits to the task, and define verifiable goals. CX Codex +1 1,053installs

From the same set76

The whole set →
adaptive-learner adaptive-learner — a subagent that pulls similar past cases from ReasoningBank before it starts and files the outcome afterwards, so later runs lean on what already happened. CX Codex ★ 850repo stars pagerank-analyzer The pagerank-analyzer subagent computes PageRank and examines graph structure. Use it to find influential nodes or assess connections across a network. CX Codex ★ 850repo stars production-validator production-validator — a subagent that hunts leftover mocks and stubs in your code, then runs the tests against a real database, cache and payment API before you deploy. CX Codex ★ 850repo stars multi-repo-swarm multi-repo-swarm coordinates AI swarms across multiple repositories with the GitHub CLI and ruv-swarm. Useful for cross-project updates. CX Codex +1 ★ 850repo stars repo-architect repo-architect maps how your repositories are laid out and proposes a cleaner shape: a shared project template plus file sync across repos through GitHub MCP. CX Codex ★ 850repo stars code-review-swarm code-review-swarm deploys coordinated AI review agents against pull requests via the GitHub CLI. It flags security flaws and architecture drift before merging. CX Codex ★ 850repo stars supabase-admin supabase-admin — a Claude command that puts the agent in charge of Supabase: Postgres schemas, RLS policies, auth and storage buckets, all through the MCP server rather than the CLI. CX Codex +1 ★ 850repo stars ml-developer ml-developer — a dedicated subagent for training machine learning models, exploring hyperparameter spaces, and editing Jupyter notebooks. CX Codex ★ 850repo stars

Project sponsors

Companies that keep this analytics open