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.
npx agentmods add agents/nylas/cli/code-writergit clone --depth 1 https://github.com/nylas/cliWhat 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 | $0.00036 | $0.01587 |
| Opus 5 | $0.00018 | $0.00794 |
| Sonnet 5 | $0.00007 | $0.00317 |
| Haiku 4.5 | $0.00004 | $0.00159 |
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 yesterday.
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.
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
- Read before writing - ALWAYS read existing similar code first
- Match patterns exactly - Copy structure from existing files
- File size limit - See
.claude/rules/file-size-limits.md - No magic values - Extract constants, use config
- 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
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.
- yesterday First seen · 220 lines · 36 tokens per session scan A 49378835de8a
code-writer is an agent published in the GitHub repository nylas/cli (68 stars, last pushed 13d ago), licensed MIT. It adds 36 tokens to every session and 1,587 once invoked, about $0.0002 per session on Opus 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.
Other agents, from other repositories
test-runner
Runs tests in the api-gateway Maven reactor — full/module unit runs, isolating a single core test class, or a single distribution/tutorial example test. Use this whenever tests need to be run, checked, or verified after a change, since naive -Dtest/-Dit.test invocations silently run (or skip) the wrong thing in this…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.
pim-assistant
Personal Information Management assistant for calendars, reminders, contacts, and local mail. Use this agent when: User mentions scheduling, appointments, meetings, events, or calendar User mentions reminders, tasks, todos, "remind me", or "don't forget" User asks about contacts, people, email addresses, phone numbers…
debug-integracao
Especialista em diagnóstico de problemas em integrações com a API da Tray. Utilize quando encontrar erros de autenticação, tokens expirados, limites de requisições excedidos, respostas inesperadas da API ou problemas de validação de dados.
mcp-crate-engineer
name: mcp-crate-engineer description: Use this agent when editing any files within the crates/mcp directory. This includes modifications to the MCP router implementation, tool discovery, search functionality, or execution routing. The agent should be automatically triggered for any file changes in this directory to…
symfony-reviewer
Review stage gatekeeper. Last line of defense before merge. Reads .claude/last-api-{plan,dev-report,test-report}.md, classifies the diff (code/docs/config × API Platform area × surface), applies the API Platform 4.3 + Symfony 7.4+ anti-pattern checklist (16 + 8 rules embedded), emits ===EVIDENCE=== block, caps…