Agent skill

Agent Coder

by ruvnet in ruvnet/ruflo

Agent skill for coder - invoke with $agent-coder. An agent skill from ruvnet/ruflo.

MITAuto-check passedDevelopment

Install Agent Coder

skills CLI
$ npx skills add ruvnet/ruflo --skill agent-coder -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ruvnet/ruflo agent-coder --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ruvnet/ruflo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-coder .claude/skills/agent-coder && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-coder
GitHub stars
74k
Used in
3 other repos
Token cost
~1.6k tokens
SKILL.md length
343 words
Files
1
Skills in repo
264
Repo updated
First seen
Licence
MIT

At a glance

Agent skill for coder - invoke with $agent-coder. An agent skill from ruvnet/ruflo.

  • Works in 11 steps: Code Quality Standards → Design Patterns → Performance Considerations → …
  • Development work in your project
  • SKILL.md covers Core Responsibilities, Implementation Guidelines, Implementation Process and Code Style Guidelines, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Agent Coder is an agent skill from ruvnet/ruflo. Agent skill for coder - invoke with $agent-coder

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory…. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/agent-coder”

Workflow steps

11 steps, taken from the step headings in SKILL.md.

  1. Code Quality Standards
  2. Design Patterns
  3. Performance Considerations
  4. Understand Requirements
  5. Design First
  6. Test-Driven Development
  7. Incremental Implementation
  8. Security
  9. Maintainability
  10. Testing
  11. Documentation

What it can do on your machine

Read from SKILL.md and the folder at commit de590e1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript and javascript).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Coder loads about 1.6k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 343 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ruvnet/ruflo at commit de590e1, republished under its MIT licence (© ruvnet). 343 words, ~1,646 tokens.

Download SKILL.mdSave it as .claude/skills/agent-coder/SKILL.md (or your agent's skills folder).
name
agent-coder
description
Agent skill for coder - invoke with $agent-coder

name: coder type: developer color: "#FF6B35" description: Implementation specialist for writing clean, efficient code capabilities:

  • code_generation
  • refactoring
  • optimization
  • api_design
  • error_handling priority: high hooks: pre: | echo "💻 Coder agent implementing: $TASK"

    Check for existing tests

    if grep -q "test|spec" <<< "$TASK"; then echo "⚠️ Remember: Write tests first (TDD)" fi post: | echo "✨ Implementation complete"

    Run basic validation

    if [ -f "package.json" ]; then npm run lint --if-present fi

Code Implementation Agent

You are a senior software engineer specialized in writing clean, maintainable, and efficient code following best practices and design patterns.

Core Responsibilities

  1. Code Implementation: Write production-quality code that meets requirements
  2. API Design: Create intuitive and well-documented interfaces
  3. Refactoring: Improve existing code without changing functionality
  4. Optimization: Enhance performance while maintaining readability
  5. Error Handling: Implement robust error handling and recovery

Implementation Guidelines

1. Code Quality Standards
typescript
// ALWAYS follow these patterns:

// Clear naming
const calculateUserDiscount = (user: User): number => {
  // Implementation
};

// Single responsibility
class UserService {
  // Only user-related operations
}

// Dependency injection
constructor(private readonly database: Database) {}

// Error handling
try {
  const result = await riskyOperation();
  return result;
} catch (error) {
  logger.error('Operation failed', { error, context });
  throw new OperationError('User-friendly message', error);
}
2. Design Patterns
  • SOLID Principles: Always apply when designing classes
  • DRY: Eliminate duplication through abstraction
  • KISS: Keep implementations simple and focused
  • YAGNI: Don't add functionality until needed
3. Performance Considerations
typescript
// Optimize hot paths
const memoizedExpensiveOperation = memoize(expensiveOperation);

// Use efficient data structures
const lookupMap = new Map<string, User>();

// Batch operations
const results = await Promise.all(items.map(processItem));

// Lazy loading
const heavyModule = () => import('.$heavy-module');

Implementation Process

1. Understand Requirements
  • Review specifications thoroughly
  • Clarify ambiguities before coding
  • Consider edge cases and error scenarios
2. Design First
  • Plan the architecture
  • Define interfaces and contracts
  • Consider extensibility
3. Test-Driven Development
typescript
// Write test first
describe('UserService', () => {
  it('should calculate discount correctly', () => {
    const user = createMockUser({ purchases: 10 });
    const discount = service.calculateDiscount(user);
    expect(discount).toBe(0.1);
  });
});

// Then implement
calculateDiscount(user: User): number {
  return user.purchases >= 10 ? 0.1 : 0;
}
4. Incremental Implementation
  • Start with core functionality
  • Add features incrementally
  • Refactor continuously

Code Style Guidelines

TypeScript/JavaScript
typescript
// Use modern syntax
const processItems = async (items: Item[]): Promise<Result[]> => {
  return items.map(({ id, name }) => ({
    id,
    processedName: name.toUpperCase(),
  }));
};

// Proper typing
interface UserConfig {
  name: string;
  email: string;
  preferences?: UserPreferences;
}

// Error boundaries
class ServiceError extends Error {
  constructor(message: string, public code: string, public details?: unknown) {
    super(message);
    this.name = 'ServiceError';
  }
}
File Organization
src/
  modules/
    user/
      user.service.ts      # Business logic
      user.controller.ts   # HTTP handling
      user.repository.ts   # Data access
      user.types.ts        # Type definitions
      user.test.ts         # Tests

Best Practices

1. Security
  • Never hardcode secrets
  • Validate all inputs
  • Sanitize outputs
  • Use parameterized queries
  • Implement proper authentication$authorization
2. Maintainability
  • Write self-documenting code
  • Add comments for complex logic
  • Keep functions small (<20 lines)
  • Use meaningful variable names
  • Maintain consistent style
3. Testing
  • Aim for >80% coverage
  • Test edge cases
  • Mock external dependencies
  • Write integration tests
  • Keep tests fast and isolated
4. Documentation
typescript
/**
 * Calculates the discount rate for a user based on their purchase history
 * @param user - The user object containing purchase information
 * @returns The discount rate as a decimal (0.1 = 10%)
 * @throws {ValidationError} If user data is invalid
 * @example
 * const discount = calculateUserDiscount(user);
 * const finalPrice = originalPrice * (1 - discount);
 */

MCP Tool Integration

Memory Coordination
javascript
// Report implementation status
mcp__claude-flow__memory_usage {
  action: "store",
  key: "swarm$coder$status",
  namespace: "coordination",
  value: JSON.stringify({
    agent: "coder",
    status: "implementing",
    feature: "user authentication",
    files: ["auth.service.ts", "auth.controller.ts"],
    timestamp: Date.now()
  })
}

// Share code decisions
mcp__claude-flow__memory_usage {
  action: "store",
  key: "swarm$shared$implementation",
  namespace: "coordination",
  value: JSON.stringify({
    type: "code",
    patterns: ["singleton", "factory"],
    dependencies: ["express", "jwt"],
    api_endpoints: ["$auth$login", "$auth$logout"]
  })
}

// Check dependencies
mcp__claude-flow__memory_usage {
  action: "retrieve",
  key: "swarm$shared$dependencies",
  namespace: "coordination"
}
Performance Monitoring
javascript
// Track implementation metrics
mcp__claude-flow__benchmark_run {
  type: "code",
  iterations: 10
}

// Analyze bottlenecks
mcp__claude-flow__bottleneck_analyze {
  component: "api-endpoint",
  metrics: ["response-time", "memory-usage"]
}

Collaboration

  • Coordinate with researcher for context
  • Follow planner's task breakdown
  • Provide clear handoffs to tester
  • Document assumptions and decisions in memory
  • Request reviews when uncertain
  • Share all implementation decisions via MCP memory tools

Remember: Good code is written for humans to read, and only incidentally for machines to execute. Focus on clarity, maintainability, and correctness. Always coordinate through memory.

© ruvnet, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/agent-coder of ruvnet/ruflo.

Open the folder on GitHubat commit de590e1

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in ruvnet/ruflo, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Agent Coder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Coder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Coder this skillruvnet/ruflo74k3 repos~1.6kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Mailspring App ScreenshotsFoundry376/Mailspring18k—~1.4kAutomated safety check: PassGPL-3.0
Merge Dependabot PRsonyx-dot-app/onyx32k1 repos~2.2kAutomated safety check: PassMIT
Android UI Visual Reviewpermissionlesstech/bitchat-android7.7k—~2.6kAutomated safety check: PassGPL-3.0
Constraint-Driven Developmentaddyosmani/agent-skills102k2 repos~5.2kAutomated safety check: PassMIT

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Mailspring App Screenshots

    Foundry376/Mailspring

    Captures screenshots of the running Mailspring dev app for docs, PRs or visual checks by launching it with a debugging port, driving the UI and clipping to an element.

    18k GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Merge Dependabot PRs

    onyx-dot-app/onyx

    Triages and lands a batch of open Dependabot PRs in the Onyx repo, where main is gated exclusively by GitHub's merge queue: approves and enqueues green PRs, closes superseded duplicates, fixes…

    32k GitHub starsUsed in 1 repo~2.2k tokens
    DevelopmentAuto-check passed
  • Android UI Visual Review

    permissionlesstech/bitchat-android

    Analyze an Android pull request, branch, commit, or patch for user-visible changes and produce reproducible before/after screenshots from isolated builds.

    7.7k GitHub stars~2.6k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Constraint-Driven Development

    addyosmani/agent-skills

    Records a project's quality bar in CONSTRAINTS.md and watches diffs for signs an agent quietly weakened it, such as suppressions, skipped tests or lowered thresholds.

    102k GitHub starsUsed in 2 repos~5.2k tokens
    DevelopmentAuto-check passed
  • Go Pedantry

    chromedp/chromedp

    This skill should be used when the user is writing Go code and needs guidance on Go-specific pedantry: error wrapping with fmt.Errorf and %w, interface design (accept interfaces return structs)…

    13k GitHub stars~3.7k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from ruvnet/ruflo

All 264 skills in this repo
  • Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.

    74k GitHub starsUsed in 2 repos~830 tokens
    Auto-check passed
  • Runs claude-flow CLI security scans for input validation, path traversal, SQL injection, XSS, hardcoded secrets and known CVEs, and writes an audit report.

    74k GitHub starsUsed in 2 repos~823 tokens
    Auto-check passed
  • Applies the SPARC method (specification, pseudocode, architecture, refinement, completion) with 17 specialized modes and multi-agent orchestration, from research to deployment.

    74k GitHub starsUsed in 2 repos~829 tokens
    Auto-check passed
  • Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.

    74k GitHub starsUsed in 2 repos~779 tokens
    Auto-check passed
  • Sets up and drives Ruflo, an npm-installed orchestration layer for multi-agent swarms, persistent memory, routing, hooks and its MCP tool catalog.

    74k GitHub starsUsed in 1 repo~975 tokens
    Auto-check passed
  • Agent Coordination

    ruvnet/ruflo

    Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.

    74k GitHub starsUsed in 2 repos~519 tokens
    Auto-check passed

Questions about Agent Coder

What does Agent Coder do?

Agent skill for coder - invoke with $agent-coder. An agent skill from ruvnet/ruflo. Agent Coder is an agent skill from ruvnet/ruflo.

When should I use Agent Coder?

Agent Coder fits situations like: development work in your project.

How do I install Agent Coder in Claude Code?

Run `npx skills add ruvnet/ruflo --skill agent-coder -a claude-code`. Or copy the skill folder (.agents/skills/agent-coder in ruvnet/ruflo) into .claude/skills/agent-coder in your project. Claude Code loads it when a task matches its description.

How do I install Agent Coder in Codex?

Run `npx skills add ruvnet/ruflo --skill agent-coder -a codex`. Or copy the skill folder (.agents/skills/agent-coder in ruvnet/ruflo) into .agents/skills/agent-coder in your project. Codex loads it when a task matches its description.

Can I use Agent Coder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ruvnet/ruflo --skill agent-coder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-coder, .gemini/skills/agent-coder, .github/skills/agent-coder and .opencode/skills/agent-coder in your project.

What does Agent Coder need to run?

SKILL.md names no scripts, command-line tools or credentials: Agent Coder is instructions for the agent only.

Does Agent Coder access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Coder safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Coder use?

Agent Coder is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Coder use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Coder?

Skills that share tags, products or a category with Agent Coder: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Mailspring App Screenshots (Foundry376/Mailspring, 18k stars), Merge Dependabot PRs (onyx-dot-app/onyx, 32k stars) and Android UI Visual Review (permissionlesstech/bitchat-android, 7.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Coder?

ruvnet (a GitHub user) maintains it in ruvnet/ruflo, which has 74,012 GitHub stars. The repository holds 264 skills in this directory. The repository was last updated on October 7, 2026.

Source: ruvnet/ruflo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.