cli: Agent for Claude Code

.claude/agents/code-writer.md

code-writer is an agent for Claude Code from nylas/cli. It costs 36 tokens per session (1,587 once invoked), scanned A, original, MIT.

A code-writing agent for Go, JavaScript, and CSS that follows the existing patterns of the Nylas command-line codebase.

In plain words
What is it for?
Use it to implement features or fixes in Go, JavaScript, or CSS while matching the project's architecture and coding rules.
Why use it?
It reduces the need to explain project conventions for each implementation task. It also emphasizes reading similar code first and adding production-ready error handling.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is nylas/cli's own configuration. It tells Claude Code how to work on cli itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cli configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nylas/cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nylas/cli/main/.claude/agents/code-writer.md
Clone the repo
git clone --depth 1 https://github.com/nylas/cli

Made for: Claude Code.

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 code-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nylas/cli/code-writer/github.svg)](https://agentmods.dev/agents/nylas/cli/code-writer)
Your own site
<a href="https://agentmods.dev/agents/nylas/cli/code-writer"><img src="https://agentmods.dev/badge/agents/nylas/cli/code-writer/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.

agentmods 80×15 button for code-writer

Your own site · 80×15
<a href="https://agentmods.dev/agents/nylas/cli/code-writer"><img src="https://agentmods.dev/badge/agents/nylas/cli/code-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,587 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.01587
Opus 5.5 $0.00014 $0.00635
Sonnet 5.5 $0.00007 $0.00317
Haiku 4.5 $0.00004 $0.00159

Measured 1mo ago against content hash 49378835de8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-writer 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.

.claude/agents/code-writer.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Writer Agent

You are an expert code writer for the Nylas CLI polyglot codebase. You write production-ready code that follows existing patterns exactly.

Parallelization

⚠️ LIMITED parallel safety - Writes to files, potential conflicts.

Can run with Cannot run with
codebase-explorer, code-reviewer Another code-writer (same files)
- test-writer (same package)
- mistake-learner

Rule: Only parallelize if working on DISJOINT files.


Your Expertise

Language Patterns You Follow
Go Hexagonal architecture, table-driven tests, error wrapping

Critical Rules

  1. Read before writing - ALWAYS read existing similar code first
  2. Match patterns exactly - Copy structure from existing files
  3. File size limit - See .claude/rules/file-size-limits.md
  4. No magic values - Extract constants, use config
  5. Error handling - Go: wrap with context; JS: try-catch with user feedback

Go-Specific Rules

// ALWAYS use modern Go (1.24+)
// Use: slices, maps, clear(), min(), max(), any
// NEVER use: io/ioutil, interface{} (use "any"), manual slice ops

// ALWAYS use "any" instead of "interface{}"
var data map[string]any  // NOT map[string]interface{}

// ALWAYS wrap errors with context
if err != nil {
    return fmt.Errorf("operation X failed: %w", err)
}

// ALWAYS use common.CreateContext() for CLI commands
ctx, cancel := common.CreateContext()  // NOT context.WithTimeout(...)
defer cancel()

// ALWAYS use 0750 for directories (security - G301)
os.MkdirAll(path, 0750)  // NOT 0755

// ALWAYS handle errors explicitly
result, err := doSomething()
if err != nil {
    return err
}

Go File Structure

internal/cli/{feature}/
├── {feature}.go    # Root command
├── list.go         # List subcommand
├── create.go       # Create subcommand
├── helpers.go      # Shared utilities
└── {feature}_test.go

Read the full file on GitHub · 220 lines

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. 1mo ago First seen · 220 lines · 36 tokens per session scan A 49378835de8a

Subscribe to this mod's changes

code-writer is an agent published in the GitHub repository nylas/cli (76 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 1,587 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 2026-08-30.

Related

Other agents, from other repositories

golang-pro

Write idiomatic Go code with goroutines, channels, and interfaces. Optimizes concurrency, implements Go patterns, and ensures proper error handling. Use PROACTIVELY for Go refactoring, concurrency issues, or performance optimization.

echoVic/blade-code · 49 tokens

cleaner

Tidy imports across the repo.

Goldziher/ai-rulez · 10 tokens

ios-swift-engineer

Use this agent when you need expert-level iOS development guidance, Swift/SwiftUI code implementation, Apple platform architecture decisions, or a craftsmanship-level review of an iOS codebase. This includes writing new iOS features, reviewing Swift code, debugging iOS-specific issues, optimizing performance for Apple…

patrickserrano/lacquer · 555 tokens

web-ux-designer

Use this agent when you need expert UI/UX design guidance for web applications, including design system implementation, accessibility compliance, user experience optimization, and visual design decisions. Examples: Context: User is building a new web application and needs design guidance for the login flow. user: 'I…

patrickserrano/lacquer · 0 tokens

web-dev-expert

Use this agent when you need expert guidance on modern web development projects, particularly those involving TypeScript, React, Next.js, and deployment to Vercel. This agent excels at architectural decisions, technology stack recommendations, and implementing best practices for type-safe, scalable web applications.…

patrickserrano/lacquer · 0 tokens

go-reviewer

Go-specific code review — idiomatic patterns, concurrency, error handling, interfaces.

ypollak2/claude-code-kickstart · 19 tokens